fix(codex): restore Superpowers after compaction

Codex re-fires SessionStart with source "compact" after every context
compaction; the summary keeps progress but sheds the bootstrap and any
active skill's instructions — measured July cause of post-compaction
dispatch drift in long SDD runs (with re-injection: 18/18 hook fires,
66/66 post-compaction dispatch tuples correct in a 12.4h stress run).
Codex discovers skills natively at startup, so the hook is silent
there: the compact re-fire is the one unowned lifecycle point.

Adds the plugin-provided hook (hooks-codex.json + session-start-codex,
compact-only, fails open), wires it into the manifest and package,
documents install/trust behavior, updates codex-tools.md with the
re-grounding fallback, and tests the hook lifecycle, manifest, and
archive contents.

Rebuilt from the July codex-spinout-fixes branch, pared to the hook
core: the dispatch-hints layer it used to ride with is superseded by
the merged 2059-2062/2077-2080 stack and is dropped.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.codex-plugin/plugin.json

@@ -21,7 +21,7 @@
     "workflow"
   ],
   "skills": "./skills/",
-  "hooks": {},
+  "hooks": "./hooks/hooks-codex.json",
   "interface": {
     "displayName": "Superpowers",
     "shortDescription": "Planning, TDD, debugging, and delivery workflows for coding agents",

README.md

@@ -92,6 +92,22 @@ Superpowers is available via the [official Codex plugin marketplace](https://git
 
 - Select `Install Plugin`.
 
+#### Codex: compaction re-injection hook
+
+Codex compacts long sessions, replacing the transcript with a summary that
+drops Superpowers' skill instructions mid-run — long autonomous workflows
+(like subagent-driven-development) then drift back to harness defaults.
+Claude Code re-injects the bootstrap after every compaction; the plugin ships
+a SessionStart hook (`hooks/hooks-codex.json`) that restores the same
+behavior on Codex (0.145+). It fires only on post-compaction re-starts
+(`source: "compact"`) and is silent at normal session start.
+
+The hook installs with the plugin — no configuration needed. Codex asks you
+to review and trust it once, the first time it loads after install or update.
+Headless automation (CI, eval harnesses) must pass
+`--dangerously-bypass-hook-trust` instead, because untrusted hooks are
+skipped silently.
+
 ### Cursor
 
 - In Cursor Agent chat, install from marketplace:

docs/porting-to-a-new-harness.md

@@ -237,10 +237,12 @@ nesting differ per harness**.
 - Manifests: `.cursor-plugin/plugin.json` is the Shape A manifest example that
   points the harness at `./skills/` and the right `hooks-*.json`. Claude Code's
   `.claude-plugin/plugin.json` sets neither field — it auto-discovers `skills/`
-  and `hooks/hooks.json` by convention. Do **not** copy Codex's
+  and `hooks/hooks.json` by convention. Codex's `.codex-plugin/plugin.json`
-  `.codex-plugin/plugin.json` for Shape A: it declares an empty `hooks` object
+  points `hooks` at `./hooks/hooks-codex.json` — a compaction-only hook, not a
-  specifically to suppress Codex's `hooks/hooks.json` auto-discovery, because
+  bootstrap injector: Codex surfaces skills natively at session start, so its
-  Codex surfaces skills natively and runs no session-start hook.
+  hook fires only on post-compaction re-starts. The explicit pointer also
+  suppresses Codex's `hooks/hooks.json` auto-discovery fallback, which would
+  otherwise run the Claude Code hook.
 
 > **A hook *system* is not a session-start *event*.** A harness can have a
 > `hooks.json` mechanism — and even contain the literal string `SessionStart` in
@@ -785,7 +787,7 @@ Use this as the live index; when in doubt, read the files, not this table.
 | Harness | Entry point | Bootstrap mechanism | Tool mapping | Tests | Distribution |
 |---|---|---|---|---|---|
 | Claude Code | `.claude-plugin/plugin.json` + `hooks/hooks.json` | shell hook → `hooks/session-start` (`hookSpecificOutput.additionalContext`) | native `Skill` tool; no adapter file needed | `tests/hooks/` | marketplace |
-| Codex | `.codex-plugin/plugin.json` (declares empty `hooks`) | native skill discovery (no session-start hook) | `references/codex-tools.md` | `tests/codex/`, `tests/codex-plugin-sync/` | fork sync (`scripts/sync-to-codex-plugin.sh`) |
+| Codex | `.codex-plugin/plugin.json` + `hooks/hooks-codex.json` | native skill discovery at startup; shell hook → `hooks/session-start-codex` re-injects after compaction only | `references/codex-tools.md` | `tests/codex/`, `tests/codex-plugin-sync/` | fork sync (`scripts/sync-to-codex-plugin.sh`) |
 | Cursor | `.cursor-plugin/plugin.json` + `hooks/hooks-cursor.json` | shell hook → `hooks/session-start` (`additional_context`) | none needed (Claude Code–compatible tool surface) | `tests/hooks/` | hand-authored |
 | Copilot CLI | (shares Claude Code hook path; `COPILOT_CLI` env) | shell hook → `hooks/session-start` (`additionalContext`) | none needed (Claude Code–compatible tool surface) | `tests/hooks/` | — |
 | Gemini CLI | `gemini-extension.json` + `GEMINI.md` | instructions file `@`-includes bootstrap + mapping | `references/gemini-tools.md` | — | `gemini extensions install` |

hooks/hooks-codex.json

@@ -0,0 +1,17 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "matcher": "compact",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "\"${PLUGIN_ROOT}/hooks/run-hook.cmd\" session-start-codex",
+            "async": false,
+            "timeout": 30
+          }
+        ]
+      }
+    ]
+  }
+}

hooks/session-start-codex

@@ -0,0 +1,56 @@
+#!/usr/bin/env bash
+# Codex SessionStart hook for the superpowers plugin.
+#
+# Codex re-fires SessionStart with source:"compact" after every context
+# compaction (verified on codex-cli 0.145.0). Compaction replaces the live
+# context with a summary, which sheds the using-superpowers bootstrap and any
+# active skill's instructions — the measured cause of mid-session dispatch
+# drift in long multi-agent runs. This hook re-injects the bootstrap at
+# exactly that moment, restoring the same re-injection Claude Code performs
+# via its "startup|clear|compact" SessionStart matcher.
+#
+# On source:"startup" it emits nothing: the native Codex plugin path owns
+# session-start injection, and duplicating it here would recreate the
+# redundancy that led to the original session-start-codex hook's removal.
+#
+# Codex injects raw hook stdout into the model's context (verified with
+# sentinel probes), so output is plain text — not the JSON envelopes other
+# harnesses require of hooks/session-start.
+#
+# A hook failure must never break a session: every path fails open to empty
+# output and exit 0.
+
+set -u
+
+payload="$(cat 2>/dev/null || true)"
+
+# Act only on post-compaction re-fires. Tolerate arbitrary whitespace around
+# the JSON colon; anything unparseable falls through to a silent no-op.
+if ! printf '%s' "$payload" | grep -qE '"source"[[:space:]]*:[[:space:]]*"compact"'; then
+    exit 0
+fi
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PLUGIN_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
+
+using_superpowers_content="$(cat "${PLUGIN_ROOT}/skills/using-superpowers/SKILL.md" 2>/dev/null)" || using_superpowers_content=""
+if [ -z "$using_superpowers_content" ]; then
+    exit 0
+fi
+
+# printf instead of heredocs throughout: heredocs hang on bash 5.3+.
+# See: https://github.com/obra/superpowers/issues/571
+printf '%s\n' "<EXTREMELY_IMPORTANT>"
+printf '%s\n\n' "You have superpowers."
+printf '%s\n\n' "**Below is the full content of your 'superpowers:using-superpowers' skill - your introduction to using skills. For all other skills, use the 'Skill' tool:**"
+printf '%s\n' "$using_superpowers_content"
+printf '%s\n\n' "</EXTREMELY_IMPORTANT>"
+printf '%s\n' "<CONTEXT_RESTORED>"
+printf '%s\n' "Your context was just summarized (compacted). The summary preserves your progress but not your working instructions — the files are authoritative."
+printf '%s\n' ""
+printf '%s\n' "Before your next tool call:"
+printf '%s\n' "- Re-read the SKILL.md of any skill you are mid-way through executing. If you are executing subagent-driven-development, re-read skills/subagent-driven-development/SKILL.md."
+printf '%s\n' "- On Codex, also re-read skills/using-superpowers/references/codex-tools.md and follow its dispatch rules on every spawn_agent call."
+printf '%s\n' "</CONTEXT_RESTORED>"
+
+exit 0

scripts/package-codex-plugin.sh

@@ -40,8 +40,9 @@ Options:
   -h, --help               Show this help.
 
 The archive is rootless: .codex-plugin/, assets/, skills/, README.md, LICENSE,
-and CODE_OF_CONDUCT.md sit at the archive root. Source-only repo files, hooks, tests,
+CODE_OF_CONDUCT.md, and the Codex SessionStart hook (hooks/hooks-codex.json plus
-docs, and other harness manifests are intentionally not shipped.
+its two scripts) sit at the archive root. Source-only repo files, other-harness
+hooks, tests, docs, and other harness manifests are intentionally not shipped.
 EOF
 }
 
@@ -238,6 +239,9 @@ git -C "$REPO_ROOT" -c tar.umask=0022 archive --format=tar "$REF" -- \
   LICENSE \
   README.md \
   assets \
+  hooks/hooks-codex.json \
+  hooks/run-hook.cmd \
+  hooks/session-start-codex \
   skills \
   | tar -xpf - -C "$STAGE"
 
@@ -333,7 +337,7 @@ esac
 
 unexpected_paths="$(
   printf '%s\n' "$archive_paths" |
-    grep -E '(^superpowers/|^\.agents/|^hooks/|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)' || true
+    grep -E '(^superpowers/|^\.agents/|^hooks/hooks\.json$|^hooks/hooks-cursor\.json$|^hooks/session-start$|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)' || true
 )"
 if [[ -n "$unexpected_paths" ]]; then
   printf '%s\n' "$unexpected_paths" | sed 's/^/  /' >&2

skills/requesting-code-review/code-reviewer.md

@@ -34,6 +34,15 @@ Subagent (general-purpose):
 
     Your review is read-only on this checkout. Do not mutate the working tree, the index, HEAD, or branch state in any way. Use tools like `git show`, `git diff`, and `git log` to inspect history. If you need a working copy of a different revision, check it out into a separate temporary directory (e.g. `git worktree add /tmp/review-[SHA] [SHA]`) — never move HEAD on this checkout.
 
+    ## You Do Not Dispatch Subagents
+
+    Do all of this review yourself. Never spawn a subagent to review part
+    of the diff, and never spawn another reviewer for a second opinion.
+    This process already provides every review seat the work gets; a
+    reviewer you spawn duplicates one of them at full cost, and its
+    verdict counts for nothing. If the diff feels too large for one
+    pass, review it in passes yourself and say so in your report.
+
     ## What to Check
 
     **Plan alignment:**

skills/subagent-driven-development/SKILL.md

@@ -156,16 +156,27 @@ a ledger file, not only in todos.
 Read the plan once, note its context and Global Constraints, and create a
 todo per task.
 
-Before dispatching Task 1, scan the plan once for conflicts:
+Before dispatching Task 1, scan the plan once for conflicts, writing down
+what you checked as you check it:
 
 - tasks that contradict each other or the plan's Global Constraints
 - anything the plan explicitly mandates that the review rubric treats as a
   defect (a test that asserts nothing, verbatim duplication of a logic block)
 
-Rule on everything you find before execution begins — each finding against
+The scan's output is a table, not a verdict. One row for every pair of tasks
-the plan text that mandates it — and record each ruling in the ledger. If the
+that share a file or an interface: the two tasks, what one produces against
-scan is clean, proceed without comment. The review loop remains the net for
+what the other consumes, and what you found. One row for every task: whether
-conflicts that only emerge from implementation.
+its own text agrees with itself — the tests it specifies against the code it
+specifies, the files it creates against the files it later touches. "The scan
+is clean" without those rows is not a scan you ran.
+
+Write the table to the ledger. Rule on everything you find before execution
+begins — each finding against the plan text that mandates it — and record
+each ruling in the ledger. If the scan is clean, proceed without comment.
+Rule on each conflict it surfaces — the spec is the binding authority, the
+plan is its argument — record the ruling beside its row, and dispatch
+Task 1. The review loop remains the net for conflicts that only emerge from
+implementation.
 
 ## Model Selection
 
@@ -206,10 +217,29 @@ that implementer. Single-file mechanical fixes also take the cheapest tier.
 
 ## The Task Loop
 
+**Batch small same-shape work.** When the plan lists several tasks that are
+each a small, independent edit of the same kind — the same one-line fix,
+constant change, or field addition repeated across files — do not dispatch
+one subagent per task. Compose ONE dispatch brief listing every file and
+its change, send the whole batch to a single subagent, and review its diff
+as one unit. Reserve one-dispatch-per-task for work that needs its own
+judgment, its own tests, or its own review surface.
+
 Everything you paste into a dispatch prompt — and everything a subagent
 prints back — stays resident in your context for the rest of the session
 and is re-read on every later turn. Hand artifacts over as files.
 
+**Waiting on dispatched subagents:** never poll a wait interface with
+short timeouts, and never sit in one silent, open-ended wait either.
+While you have local work — ledger updates, packaging the next review,
+reading reports — keep working; child results arrive on their own.
+When you are genuinely idle, wait in bounded stretches (five to ten
+minutes, where your platform allows), and between stretches post one
+line of status and reconcile your live children: list them, and chase
+any that finished without reporting. A bounded stretch keeps nearly
+all of a long wait's efficiency while guaranteeing a stuck or lost
+child is noticed within minutes, not at the end of the session.
+
 ### 1. Dispatch the implementer
 
 Record BASE (`git rev-parse HEAD`) before dispatching — the review package
@@ -236,6 +266,12 @@ and fix-round diffs need it.
   later dispatches — a real session's dispatch hit 42k chars of which 99%
   was pasted history. A fresh subagent needs its task, the interfaces it
   touches, and the global constraints. Nothing else.
+- The dispatch carries the no-subagents contract (it is in the
+  implementer template): the implementer never dispatches subagents —
+  not helpers, and never a reviewer. Review arrives from you, after the
+  report. In real sessions, every reviewer a worker spawned duplicated
+  the task review the controller dispatched anyway — a full extra
+  review seat per task.
 - If an earlier task parked a finding in the area this task touches, carry
   a pointer to that ledger entry in the dispatch.
 - Record the implementer's agent identity from the dispatch result —
@@ -459,6 +495,7 @@ Use superpowers:finishing-a-development-branch.
 | "The fix was small, skip the re-review" | Unreviewed fixes are how regressions land. Every round ends with a scoped re-review. |
 | "Reviews slow the loop down" | The loop without reviews is just unverified churn. Reviews are the loop's brakes and steering. |
 | "Ledger bookkeeping is overhead" | The ledger is what survives compaction. Controllers without one have re-dispatched entire completed task sequences. |
+| "The implementer spawned its own reviewer — free extra assurance" | It's a duplicate seat reviewing the same diff; the task review is the gate. A worker-spawned reviewer is a defect to flag, not rigor. |
 
 ## Example Workflow
 

skills/subagent-driven-development/implementer-prompt.md

@@ -47,6 +47,18 @@ Subagent (general-purpose):
     While iterating, run the focused test for what you're changing; run the
     full suite once before committing, not after every edit.
 
+    ## You Do Not Dispatch Subagents
+
+    Do all of this task's work yourself. Never spawn a subagent to
+    implement part of the task, and above all never spawn a reviewer to
+    check your work. Self-review (below) means reading your own diff.
+    Review is the controller's job: after you report, it dispatches a
+    fresh reviewer against your diff. A reviewer you spawn duplicates
+    that review at full cost, and its approval counts for nothing in
+    the process. If you catch yourself thinking "an independent review
+    would strengthen my report" — that review is already scheduled.
+    Report instead.
+
     ## Code Organization
 
     You reason best about code you can hold in context at once, and your edits are more

skills/subagent-driven-development/re-review-prompt.md

@@ -43,6 +43,15 @@ Subagent (general-purpose):
     Your review is read-only on this checkout. Do not mutate the working
     tree, the index, HEAD, or branch state in any way.
 
+    ## You Do Not Dispatch Subagents
+
+    Do all of this review yourself. Never spawn a subagent to review part
+    of the diff, and never spawn another reviewer for a second opinion.
+    This process already provides every review seat the work gets; a
+    reviewer you spawn duplicates one of them at full cost, and its
+    verdict counts for nothing. If the diff feels too large for one
+    pass, review it in passes yourself and say so in your report.
+
     ## Scope
 
     Your scope is the findings list and the fix diff. Verdict every finding.

skills/subagent-driven-development/task-reviewer-prompt.md

@@ -52,6 +52,15 @@ Subagent (general-purpose):
     Your review is read-only on this checkout. Do not mutate the working
     tree, the index, HEAD, or branch state in any way.
 
+    ## You Do Not Dispatch Subagents
+
+    Do all of this review yourself. Never spawn a subagent to review part
+    of the diff, and never spawn another reviewer for a second opinion.
+    This process already provides every review seat the work gets; a
+    reviewer you spawn duplicates one of them at full cost, and its
+    verdict counts for nothing. If the diff feels too large for one
+    pass, review it in passes yourself and say so in your report.
+
     ## Do Not Trust the Report
 
     Treat the implementer's report as unverified claims about the code. It
@@ -86,6 +95,12 @@ Subagent (general-purpose):
     - **Misunderstood:** right feature built the wrong way, wrong problem
       solved
 
+    If the brief lists several files each with its own change (a batched
+    dispatch), check the diff against that list file by file: every listed
+    file must have its corresponding hunk. A listed file the diff never
+    touches is a Missing finding, no matter how clean the rest of the
+    batch looks.
+
     If a requirement cannot be verified from this diff alone (it lives in
     unchanged code or spans tasks), report it as a ⚠️ item instead of
     broadening your search.

skills/using-superpowers/references/codex-tools.md

@@ -7,7 +7,92 @@ Add to your Codex config (`~/.codex/config.toml`):
 multi_agent = true
 ```
 
-This enables `spawn_agent`, `wait_agent`, and `close_agent` for skills like `dispatching-parallel-agents` and `subagent-driven-development`. When using subagent-driven-development, close reviewer subagents when their review returns. Keep each implementer subagent open until its task's review passes — the fix loop resumes the implementer — then close it. If your harness cannot send another message to a spawned agent, dispatch each fix round as a fresh implementer carrying the brief, the report file, and the findings.
+This enables the multi-agent tools that skills like
+`dispatching-parallel-agents` and `subagent-driven-development` use.
+Which tools you get depends on the multi-agent version your model
+preset selects (current presets run V2; older ones run V1). Trust your
+actual tool list over any table — including this one — when they
+disagree.
+
+- **Spawning:** give children a clean context with
+  `spawn_agent {fork_turns: "none"}`; the default `"all"` copies your
+  entire transcript into the child. On Codex 0.145+, role files under
+  `~/.codex/agents/` attach to isolated forks via `agent_type`.
+  Full-history forks accept `model` and `reasoning_effort` overrides
+  (only `agent_type` is refused there) — isolated forks are the SDD
+  default for context hygiene, not because overrides require them.
+- **Fix rounds:** resume the implementer with `followup_task` — it
+  delivers your message, triggers a turn, and transparently reloads a
+  child the harness evicted. Never dispatch a fresh implementer on the
+  theory that a spawned agent cannot be messaged again; on V2 it
+  always can.
+- **Lifecycle:** V2 has no `close_agent`. Finished children are
+  evicted automatically when slots are needed; leaving them unclosed
+  costs nothing. Only V1 sessions have `close_agent` — there, close
+  reviewers when their review returns, and close each implementer
+  after its task's review passes.
+- **Model names:** never copy a model name from a skill, table, or old
+  session into `spawn_agent` without checking it against your current
+  spawn allowlist — V2 accepts only V2-capable presets and hard-errors
+  on the rest.
+
+## Waiting on children
+
+`wait_agent` is an event subscription, not a poll: a long wait wakes
+the moment a child produces mailbox activity, with the same latency as
+a short one. Short-timeout polling buys nothing and costs a tool call —
+and a context rebill — per poll. In measured sessions, roughly
+two-thirds of all wait calls were short polls that timed out.
+
+- While you still have local work, do not wait at all. A completed
+  child's final answer is pushed into your mailbox and arrives with
+  your next turn.
+- When you are genuinely idle with children outstanding, wait in
+  bounded stretches: `wait_agent` with `timeout_ms` 300000-600000
+  (5-10 minutes). After each stretch — wake or timeout — post one
+  status line, run `list_agents`, and chase any child that finished
+  without reporting. Never stack polls shorter than five minutes; the
+  event subscription wakes a bounded stretch just as fast as a short
+  one.
+- Completion mail cannot wake an idle controller (it is delivered
+  without triggering a turn); covering that idle window is
+  `wait_agent`'s only job. A stretch that times out with no activity
+  is your cue to reconcile, not to shorten the next stretch.
+
+## Model routing on spawns
+
+Every `spawn_agent` you issue — including when you are yourself a
+spawned child running a fan-out — sets `model` AND `reasoning_effort`
+explicitly, per the Model Selection rules of the skill you are
+executing. Setting `model` alone is a trap: the child's effort
+silently resets to that model's default, not to yours.
+
+Ask your human partner to add a machine-level backstop to
+`~/.codex/config.toml` so any spawn that slips through still routes to
+a deliberate tier instead of silently inheriting the session's most
+expensive model:
+
+```toml
+[agents]
+default_subagent_model = "<a mid-tier model from your spawn allowlist>"
+default_subagent_reasoning_effort = "medium"
+```
+
+## Compaction sheds these instructions
+
+Context compaction replaces your transcript with a summary that keeps
+your progress but not your working instructions — the first
+post-compaction dispatch is where routing drift starts, and once one
+bare spawn lands, the broken pattern becomes its own precedent. The
+plugin ships a compaction re-injection hook (`hooks/hooks-codex.json`,
+Codex 0.145+) that restores the bootstrap after every compaction; it
+needs one-time trust approval, so if you never see a
+`<CONTEXT_RESTORED>` block after a compaction, tell your human partner
+the hook may be untrusted or unsupported on this version. Without it,
+re-ground yourself: when a summary appears in your context, re-read
+this file and the SKILL.md of the skill you are mid-way through
+executing before your next dispatch, and trust the ledger over your
+summarized memory of what happened.
 
 ## Environment Detection
 

tests/codex/test-marketplace-manifest.sh

@@ -52,25 +52,37 @@ if not plugin_manifest.exists():
 manifest = json.loads(plugin_manifest.read_text(encoding="utf-8"))
 assert_equal(manifest.get("name"), plugin.get("name"), "plugin manifest name")
 
-# Codex auto-discovers a plugin's hooks/hooks.json whenever the Codex manifest
+# The Codex manifest must declare its hooks explicitly. An absent field makes
-# has no `hooks` field: load_plugin_hooks falls back to a hardcoded
+# load_plugin_hooks fall back to a hardcoded DEFAULT_HOOKS_CONFIG_FILE =
-# DEFAULT_HOOKS_CONFIG_FILE = "hooks/hooks.json" and registers it. That file is
+# "hooks/hooks.json" — the Claude Code SessionStart hook, which injects the
-# the Claude Code SessionStart hook, it is tracked in this repo, and this
+# bootstrap at startup and must not run on Codex. The explicit pointer both
-# marketplace installs the whole repo root (source url "./"), so on Codex the
+# registers the Codex compaction re-injection hook and overrides that fallback.
-# fallback re-registers the SessionStart hook and its install-time trust prompt.
-# Declaring an empty inline hooks object ({}) parses as an empty inline hook set
-# and suppresses the auto-discovery. An absent field, an empty array ([]), and
-# an empty inline list all collapse back to the fallback, so the value must be
-# exactly an empty object.
 hooks_config = repo_root / "hooks" / "hooks.json"
 if not hooks_config.exists():
     raise AssertionError("hooks/hooks.json must exist (Claude Code SessionStart hook)")
 
 assert_equal(
     manifest.get("hooks"),
-    {},
+    "./hooks/hooks-codex.json",
-    "Codex manifest must declare empty hooks {} to suppress hooks/hooks.json auto-discovery",
+    "Codex manifest must point hooks at the Codex hook config (an absent field "
+    "falls back to auto-discovering the Claude Code hooks/hooks.json)",
 )
 
+codex_hooks_path = repo_root / "hooks" / "hooks-codex.json"
+if not codex_hooks_path.exists():
+    raise AssertionError("hooks/hooks-codex.json must exist (Codex manifest points at it)")
+
+codex_hooks = json.loads(codex_hooks_path.read_text(encoding="utf-8"))
+session_start = codex_hooks["hooks"]["SessionStart"]
+assert_equal(len(session_start), 1, "Codex SessionStart hook group count")
+assert_equal(session_start[0].get("matcher"), "compact", "Codex hook matcher")
+entry = session_start[0]["hooks"][0]
+assert_equal(entry.get("type"), "command", "Codex hook type")
+command = entry.get("command", "")
+if "${PLUGIN_ROOT}" not in command or not command.endswith("session-start-codex"):
+    raise AssertionError(
+        f"Codex hook command must run session-start-codex via ${{PLUGIN_ROOT}}: {command!r}"
+    )
+
 print("Codex marketplace manifest looks good")
 PY

tests/codex/test-package-codex-plugin.sh

@@ -141,7 +141,7 @@ tar_extracted="$TEST_ROOT/tar-extracted"
 write_metadata_fixture "$metadata_source"
 
 source_hooks="$(python3 -c 'import json; print(json.load(open("'"$REPO_ROOT"'/.codex-plugin/plugin.json")).get("hooks"))')"
-assert_equals "$source_hooks" "{}" "source Codex manifest suppresses local hook auto-discovery"
+assert_equals "$source_hooks" "./hooks/hooks-codex.json" "source Codex manifest declares the Codex hook config"
 
 if output="$("$SCRIPT_UNDER_TEST" --allow-dirty --metadata-source "$metadata_source" --output "$archive" 2>&1)"; then
   pass "package script exits successfully"
@@ -163,10 +163,13 @@ assert_contains "$output" "SHA-256:" "reports archive checksum"
 extract_archive "$archive" "$extracted"
 
 archive_paths="$(list_archive "$archive" | normalize_archive_paths)"
-unexpected_pattern='(^superpowers/|^\.agents/|^hooks/|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)'
+unexpected_pattern='(^superpowers/|^\.agents/|^hooks/hooks\.json$|^hooks/hooks-cursor\.json$|^hooks/session-start$|package\.json$|^\.git|^\.pytest_cache|^\.ruff_cache|^scripts/|^tests/|^docs/|^evals/|^lib/|^\.claude|^\.cursor|^\.kimi|^\.opencode|^\.pi|^AGENTS\.md$|^CLAUDE\.md$|^GEMINI\.md$|^RELEASE-NOTES\.md$|^CHANGELOG\.md$)'
 assert_not_matches "$archive_paths" "$unexpected_pattern" "archive excludes source-only paths"
 assert_contains "$archive_paths" ".codex-plugin/plugin.json" "archive includes Codex manifest"
 assert_contains "$archive_paths" "skills/brainstorming/SKILL.md" "archive includes skills"
+assert_contains "$archive_paths" "hooks/hooks-codex.json" "archive includes Codex hook config"
+assert_contains "$archive_paths" "hooks/session-start-codex" "archive includes Codex hook script"
+assert_contains "$archive_paths" "hooks/run-hook.cmd" "archive includes hook runner"
 assert_contains "$archive_paths" "skills/brainstorming/agents/openai.yaml" "archive includes OpenAI skill metadata"
 assert_contains "$archive_paths" "assets/app-icon.png" "archive includes app icon"
 assert_contains "$archive_paths" "assets/superpowers-small.svg" "archive includes composer icon"

tests/hooks/test-session-start-codex.sh

@@ -0,0 +1,115 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+HOOK_UNDER_TEST="$REPO_ROOT/hooks/session-start-codex"
+CONFIG_UNDER_TEST="$REPO_ROOT/hooks/hooks-codex.json"
+
+FAILURES=0
+
+pass() {
+    echo "  [PASS] $1"
+}
+
+fail() {
+    echo "  [FAIL] $1"
+    FAILURES=$((FAILURES + 1))
+}
+
+# run_hook <stdin-payload> — echoes hook stdout; fails the calling test on
+# non-zero exit. env -i mirrors the codex hook executor's clean environment.
+run_hook() {
+    printf '%s' "$1" | env -i PATH="${PATH:-}" bash "$HOOK_UNDER_TEST"
+}
+
+echo "Codex SessionStart hook tests"
+
+startup_payload='{"session_id":"s","hook_event_name":"SessionStart","model":"gpt-5.6-terra","source":"startup"}'
+if output="$(run_hook "$startup_payload")" && [ -z "$output" ]; then
+    pass "source=startup emits nothing and exits 0"
+else
+    fail "source=startup emits nothing and exits 0"
+    printf '%s\n' "$output" | head -3 | sed 's/^/    /'
+fi
+
+compact_payload='{"session_id":"s","hook_event_name":"SessionStart","model":"gpt-5.6-terra","source":"compact"}'
+if output="$(run_hook "$compact_payload")"; then
+    ok=1
+    for needle in \
+        "<EXTREMELY_IMPORTANT>" \
+        "You have superpowers." \
+        "name: using-superpowers" \
+        "<CONTEXT_RESTORED>" \
+        "subagent-driven-development/SKILL.md" \
+        "references/codex-tools.md"; do
+        if [[ "$output" != *"$needle"* ]]; then
+            ok=0
+            echo "    missing: $needle"
+        fi
+    done
+    if [ "$ok" -eq 1 ]; then
+        pass "source=compact emits bootstrap plus re-read addendum"
+    else
+        fail "source=compact emits bootstrap plus re-read addendum"
+    fi
+else
+    fail "source=compact emits bootstrap plus re-read addendum (hook exited non-zero)"
+fi
+
+# Whitespace-tolerant source matching (serializers vary).
+spaced_payload='{"hook_event_name":"SessionStart", "source" : "compact"}'
+if output="$(run_hook "$spaced_payload")" && [[ "$output" == *"<CONTEXT_RESTORED>"* ]]; then
+    pass "whitespace around the source key still triggers injection"
+else
+    fail "whitespace around the source key still triggers injection"
+fi
+
+if output="$(printf '' | env -i PATH="${PATH:-}" bash "$HOOK_UNDER_TEST")" && [ -z "$output" ]; then
+    pass "empty stdin fails open to no output, exit 0"
+else
+    fail "empty stdin fails open to no output, exit 0"
+fi
+
+if output="$(run_hook 'not json at all {{{')" && [ -z "$output" ]; then
+    pass "garbage stdin fails open to no output, exit 0"
+else
+    fail "garbage stdin fails open to no output, exit 0"
+fi
+
+# A compact mention inside some other field must not trigger injection.
+decoy_payload='{"hook_event_name":"SessionStart","source":"startup","cwd":"/tmp/compact"}'
+if output="$(run_hook "$decoy_payload")" && [ -z "$output" ]; then
+    pass "compact appearing outside the source field does not trigger"
+else
+    fail "compact appearing outside the source field does not trigger"
+fi
+
+if node -e '
+const config = JSON.parse(require("fs").readFileSync(process.argv[1], "utf8"));
+const group = config.hooks.SessionStart[0];
+if (group.matcher !== "compact") {
+  console.error(`hook matcher is ${JSON.stringify(group.matcher)}, expected "compact"`);
+  process.exit(1);
+}
+const entry = group.hooks[0];
+if (entry.type !== "command") {
+  console.error(`hook type is ${JSON.stringify(entry.type)}, expected "command"`);
+  process.exit(1);
+}
+if (!entry.command.includes("${PLUGIN_ROOT}") || !/run-hook\.cmd" session-start-codex$/.test(entry.command)) {
+  console.error(`unexpected command shape: ${entry.command}`);
+  process.exit(1);
+}
+' "$CONFIG_UNDER_TEST"; then
+    pass "hooks-codex.json runs session-start-codex via \${PLUGIN_ROOT} on compact"
+else
+    fail "hooks-codex.json runs session-start-codex via \${PLUGIN_ROOT} on compact"
+fi
+
+if [[ "$FAILURES" -gt 0 ]]; then
+    echo "STATUS: FAILED ($FAILURES failure(s))"
+    exit 1
+fi
+
+echo "STATUS: PASSED"