docs: describe the :; label-line wrapper mechanism (#571)

bash >= 5.1 writes heredocs into a pipe pre-fork; under macOS pipe
pressure the kernel hands out 512-byte pipes and the wrapper's 1.4KB
CMDBLOCK heredoc deadlocks every hook. Label lines parse nowhere:
cmd.exe skips them as labels, POSIX shells exec away before the batch
block. Also: silent fail-open when bash or the script name is missing,
and CDPATH-proof directory resolution.

README.md

@@ -2,6 +2,31 @@
 
 Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.
 
+## Table of Contents
+
+- [Quickstart](#quickstart)
+- [How it works](#how-it-works)
+- [Commercial Services](#commercial-services)
+- [Installation](#installation)
+  - [Claude Code](#claude-code)
+  - [Antigravity](#antigravity)
+  - [Codex App](#codex-app)
+  - [Codex CLI](#codex-cli)
+  - [Cursor](#cursor)
+  - [Factory Droid](#factory-droid)
+  - [Gemini CLI](#gemini-cli)
+  - [GitHub Copilot CLI](#github-copilot-cli)
+  - [Kimi Code](#kimi-code)
+  - [OpenCode](#opencode)
+  - [Pi](#pi)
+- [The Basic Workflow](#the-basic-workflow)
+- [Community](#community)
+- [What's Inside](#whats-inside)
+- [Philosophy](#philosophy)
+- [Contributing](#contributing)
+- [Updating](#updating)
+- [License](#license)
+- [Visual companion telemetry](#visual-companion-telemetry)
 
 ## Quickstart
 
@@ -211,6 +236,14 @@ The Pi package loads the Superpowers skills and a small extension that injects t
 
 **The agent checks for relevant skills before any task.** Mandatory workflows, not suggestions.
 
+## Community
+
+Superpowers is built by [Jesse Vincent](https://blog.fsck.com) and the rest of the folks at [Prime Radiant](https://primeradiant.com).
+
+- **Discord**: [Join us](https://discord.gg/35wsABTejz) for community support, questions, and sharing what you're building with Superpowers
+- **Issues**: https://github.com/obra/superpowers/issues
+- **Release announcements**: [Sign up](https://primeradiant.com/superpowers/) to get notified about new versions
+
 ## What's Inside
 
 ### Skills Library
@@ -271,11 +304,3 @@ MIT License - see LICENSE file for details
 ## Visual companion telemetry
 
 Because skills and plugins don't provide any feedback to creators, we have no idea how many of you are using Superpowers. By default, the Prime Radiant logo on brainstorming's optional visual companion feature is loaded from our website. It includes the version of Superpowers in use. It does not include any details about your project, prompt, or coding agent. We don't see your clicks or anything about what you're building. This helps us have a rough idea of how many folks are using Superpowers and which version of Superpowers they're using. It's 100% optional. To disable this, set the environment variable `SUPERPOWERS_DISABLE_TELEMETRY` to any true value. Superpowers also honors Claude Code's `DISABLE_TELEMETRY` and `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` opt-outs.
-
-## Community
-
-Superpowers is built by [Jesse Vincent](https://blog.fsck.com) and the rest of the folks at [Prime Radiant](https://primeradiant.com).
-
-- **Discord**: [Join us](https://discord.gg/35wsABTejz) for community support, questions, and sharing what you're building with Superpowers
-- **Issues**: https://github.com/obra/superpowers/issues
-- **Release announcements**: [Sign up](https://primeradiant.com/superpowers/) to get notified about new versions

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

@@ -745,8 +745,10 @@ single file that's valid as both a Windows batch script and a Unix shell script.
 On Windows, `cmd.exe` runs the batch portion, which locates `bash` (Git for
 Windows, then `bash` on PATH) and runs the named hook script; if no bash is
 found it exits cleanly so the harness still works, just without injection. On
-Unix, the leading `:` makes the batch block a no-op and the shell runs the
+Unix, the shell executes the leading `:;` lines and `exec`s the hook script
-script directly.
+before reaching the batch block (cmd.exe skips those lines as labels).
+Heredocs are banned throughout hooks/ — see issue #571 and the fence test
+`tests/hooks/test-no-heredocs-in-hooks.sh`.
 
 Two rules this enforces, which you must respect:
 

docs/windows/polyglot-hooks.md

@@ -65,9 +65,9 @@ The path is quoted because `${CLAUDE_PLUGIN_ROOT}` may contain spaces.
 
 ## How `run-hook.cmd` Works at a High Level
 
-`run-hook.cmd` is a polyglot script: Windows treats the first block as batch
+`run-hook.cmd` is a polyglot script: its first lines start with `:;`, which
-commands, while Unix shells treat that block as a no-op heredoc and continue
+cmd.exe skips as labels and Unix shells execute — the shell execs the hook
-after it.
+before ever reaching the batch block that Windows runs.
 
 Do not copy an implementation from this document. Read `hooks/run-hook.cmd`
 directly when changing the dispatcher, and run `tests/hooks/test-session-start.sh`
@@ -89,10 +89,14 @@ afterward.
 
 ### How it works on Unix (bash/sh)
 
-1. `: << 'CMDBLOCK'` opens a heredoc on a no-op command.
+1. Each leading `:;` line is a no-op label to cmd.exe but real commands to a
-2. The entire CMD batch block is consumed by the heredoc and ignored.
+   POSIX shell.
-3. After `CMDBLOCK`, bash resolves the script directory and `exec`s the named
+2. The shell checks bash exists (silent exit 0 if not), resolves the script
-   extensionless script directly.
+   directory CDPATH-proof, and `exec`s the named extensionless script — it
+   never reads the batch block at all.
+3. Heredocs are banned in this file and all hooks/ executables (issue #571:
+   bash >= 5.1 pre-fork pipe writes deadlock on macOS under pipe pressure);
+   `tests/hooks/test-no-heredocs-in-hooks.sh` enforces the ban.
 
 ### Key design decisions
 

hooks/run-hook.cmd

@@ -1,8 +1,20 @@
-: << 'CMDBLOCK'
+:; command -v bash >/dev/null 2>&1 || exit 0
+:; [ $# -ge 1 ] || exit 0
+:; SCRIPT_DIR="$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)"
+:; SCRIPT_NAME="$1"; shift; exec bash "${SCRIPT_DIR}/${SCRIPT_NAME}" "$@"
 @echo off
 REM Cross-platform polyglot wrapper for hook scripts.
-REM On Windows: cmd.exe runs the batch portion, which finds and calls bash.
+REM On Unix: POSIX shells execute the ":;" lines above and exec away before
-REM On Unix: the shell interprets this as a script (: is a no-op in bash).
+REM reaching this batch block (":" is a no-op; cmd.exe treats lines starting
+REM with ":" as labels and skips them). If bash or the script name is
+REM missing, the wrapper exits 0 silently - hooks are optional context, never
+REM a session breaker.
+REM On Windows: cmd.exe runs this batch portion, which finds and calls bash.
+REM
+REM Heredocs are banned in this file and every hooks/ executable: bash 5.1+
+REM delivers them via a pre-fork pipe write that deadlocks on macOS under
+REM pipe pressure (issue #571). tests/hooks/test-no-heredocs-in-hooks.sh is
+REM the fence.
 REM
 REM Hook scripts use extensionless filenames (e.g. "session-start" not
 REM "session-start.sh") so Claude Code's Windows auto-detection -- which
@@ -35,12 +47,4 @@ if %ERRORLEVEL% equ 0 (
 )
 
 REM No bash found - exit silently rather than error
-REM (plugin still works, just without SessionStart context injection)
 exit /b 0
-CMDBLOCK
-
-# Unix: run the named script directly
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-SCRIPT_NAME="$1"
-shift
-exec bash "${SCRIPT_DIR}/${SCRIPT_NAME}" "$@"

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 +7,76 @@ 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"
+```
 
 ## Environment Detection
 

tests/hooks/test-no-heredocs-in-hooks.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Heredocs are banned from the hook delivery chain: bash >= 5.1 delivers
+# them through a pre-fork pipe write that deadlocks on macOS under pipe
+# pressure (issue #571; the #571 class). This fence fails the moment one
+# returns. The operator is spelled out of a variable so this file does not
+# trip its own check.
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+OP='<''<'
+FAILURES=0
+for f in "$REPO_ROOT"/hooks/*; do
+    case "$f" in *.json) continue;; esac
+    [ -f "$f" ] || continue
+    if hits="$(grep -nE "$OP" "$f")"; then
+        echo "  [FAIL] heredoc operator in ${f#"$REPO_ROOT"/}:"
+        printf '%s\n' "$hits" | sed 's/^/    /'
+        FAILURES=$((FAILURES + 1))
+    else
+        echo "  [PASS] ${f#"$REPO_ROOT"/} is heredoc-free"
+    fi
+done
+
+if [ "$FAILURES" -gt 0 ]; then
+    echo "STATUS: FAILED ($FAILURES file(s))"
+    exit 1
+fi
+echo "STATUS: PASSED"

tests/hooks/test-session-start.sh

@@ -184,6 +184,15 @@ assert_command_output \
     CLAUDE_PLUGIN_ROOT="$REPO_ROOT" \
     bash "$WRAPPER_UNDER_TEST" session-start
 
+# With no bash available, the wrapper must fail open: silent, exit 0.
+if output="$(env -i PATH=/nonexistent /bin/sh "$WRAPPER_UNDER_TEST" session-start 2>&1)" \
+   && [ -z "$output" ]; then
+    pass "wrapper with no bash on PATH is silent and exits 0"
+else
+    fail "wrapper with no bash on PATH is silent and exits 0"
+    printf '%s\n' "$output" | head -3 | sed 's/^/    /'
+fi
+
 cursor_home="$(make_home cursor)"
 assert_command_output \
     "Cursor emits top-level additional_context only" \