* feat: inject ponytail ruleset into subagents via SubagentStart hook
SessionStart additionalContext is parent-thread only, so every Task-spawned
agent ran ponytail-unaware. Add a SubagentStart hook that injects the active
ruleset into each subagent, reusing getPonytailInstructions. Native Claude
needs the hookSpecificOutput JSON form (not raw stdout), so writeHookOutput
grows a SubagentStart branch; readMode exposes the live flag.
Workflow- and team-spawned coverage is undocumented upstream; verify in a
fresh session once installed.
Closes#252
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01H1dMag33yz1Kf1jS24Aira
* fix: address QA round 1 — make hook tests hermetic + cover Codex SubagentStart
QA round 1 (panel + deepseek-v4-pro) found two real test issues:
- The new subagent block (and the pre-existing claudeEnv block) used a no-op
`delete env.PLUGIN_DATA`; run() spreads process.env, so a PLUGIN_DATA /
COPILOT_PLUGIN_DATA leaked from the shell would steer writeHookOutput into the
codex/copilot branch and silently mis-fire the native-Claude assertions.
Fixed at the source: neutralize both vars once at the top, like CLAUDE_CONFIG_DIR.
- The Codex SubagentStart branch (claude-codex-hooks.json is shared by both plugin
manifests) had zero coverage. Added a codex-path assertion.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01H1dMag33yz1Kf1jS24Aira
* fix: use PowerShell-safe command form for SubagentStart hook
Match the post-#265 'node ...; exit 0' form used by the sibling hooks. The old 'command -v node ... || exit 0' form fails tests/hooks-windows.test.js (POSIX-guard and non-blocking asserts) once this branch merges onto current main.
---------
Co-authored-by: Shane McCarron <shane.mccarron@corvexconnect.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Emeriko <dietrich.gebert@gmail.com>
#245 "Dangerously lazy": add an operational "fix the root cause, not the
symptom" directive — grep every caller of the function you touch and fix the
shared function once (the smaller diff). Validated on the agentic benchmark: on
a shared-helper bug-fix trap, baseline fixes the root cause 1/6 while ponytail
does 6/6 on both Sonnet 4.6 (the model the issue was filed on) and Opus 4.8,
verified by reading the produced code. Plain prose ("trace the flow") did not
move it; the actionable, lazy-framed directive did.
#217 "Missing rung": add ladder rung 2 "Already in this codebase? Reuse it,
don't re-write it." Propagated across SKILL.md, AGENTS.md, all agent mirror
copies, the hook fallback, and both READMEs (check-rule-copies passes).
Benchmark: 4 new deterministic quality-tier tasks (reuse-slug, reuse-money,
trace-transfer, trace-amount) with selftest-proven good/bad refs; harness gains
multi-file seed support in --selftest, distinctive-behaviour reuse detection,
and counts in-file __main__/demo() self-checks as test LOC (not source bloat)
for surgical tasks. Full writeup in
benchmarks/results/2026-06-22-issue-245-217-comprehension.md.
Also carries the in-progress todo-null benchmark task already present in the
working tree.
Co-authored-by: Dietrich Gebert <dgebert@Dietrichs-MacBook-Pro.local>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
The SessionStart nudge built a statusLine command by interpolating the
plugin's __dirname path into a double-quoted shell string. A clone path
containing shell metacharacters (quotes, &, $, backtick, ;) could break
out when the suggested command later runs via the statusline shell.
Low severity in practice: the path is the install location, so triggering
it requires installing into a maliciously-named directory, i.e. the
attacker already controls the filesystem. Hardening it anyway.
Gate the snippet behind isShellSafe() (allowlist of ordinary path chars,
allowing : \ / for normal Windows and POSIX paths). Unsafe paths fall
back to a manual-setup instruction instead of an embeddable command. An
allowlist beats a per-shell escaper, which is its own edge-case bug farm.
Refs #200
Issue #34 made the hooks honor CLAUDE_CONFIG_DIR when writing the mode flag
($CLAUDE_CONFIG_DIR/.ponytail-active), enforced by tests/hooks.test.js. But
both statusline scripts still hardcoded $HOME/.claude/.ponytail-active, so any
user with CLAUDE_CONFIG_DIR set gets no badge — or a stale mode from a
pre-migration ~/.claude flag that never updates again.
Make both scripts resolve the flag the same way getClaudeDir() does: prefer
CLAUDE_CONFIG_DIR, fall back to ~/.claude. The fallback branch is identical to
the previous behavior, so unset-env users are unaffected. Also corrects the
now-inaccurate path comment in the activation hook header.
The final writeHookOutput('SessionStart', ...) call was the only operation
in the file outside a try/catch. writeHookOutput ends in a bare
process.stdout.write, so a closed stdout / broken pipe (EPIPE) at hook exit
throws uncaught and crashes the hook with a non-zero exit code. Wrap it to
match the file's existing never-block-session-start posture.
settings.json written by Notepad or VS Code on Windows can carry a
UTF-8 BOM. JSON.parse then throws SyntaxError, the outer catch swallows
it, hasStatusline stays false, and the statusline setup nudge is never
emitted.
Strip the leading BOM before parsing, matching the existing handling in
ponytail-mode-tracker.js. (#96 added a null guard but not BOM stripping.)
The deactivation check matched the phrase anywhere in the prompt, so an
ordinary request like "add a normal mode toggle" silently turned ponytail
off for the rest of the session. Match the whole message instead (trimmed,
case-insensitive, trailing punctuation ignored) through a shared helper used
by both the Claude/Codex hook and the pi extension.
Fixes#161
Claude Code runs hooks via a non-interactive /bin/sh. On setups where node
isn't on that shell's PATH (Nix/nix-darwin, nvm, fnm), every prompt errored
with "/bin/sh: node: command not found". Guard each hook command so it runs
node only when present and exits 0 otherwise, no more per-prompt noise. The
slash-command skills are unaffected; only the always-on activation needs node.
Document the requirement in the README install section.
Closes#51.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Add GitHub Copilot plugin and marketplace manifests for Ponytail
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add Copilot hook adapters and plugin data runtime precedence
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Document Copilot plugin install flow and instruction fallback mode
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix Copilot hooks for native output context and state-only mode tracking
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* docs: add Copilot CLI namespaced command examples
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Collapse Copilot hooks into shared activate/mode-tracker
The Copilot hook files duplicated ponytail-activate.js and
ponytail-mode-tracker.js, differing only in output shape. Move that
difference into writeHookOutput (isCopilot branch) and point
copilot-hooks.json at the shared hooks. Deletes both forks (-73 lines).
Refs #1
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Align Copilot manifest version to 4.4.0 with cross-manifest parity test
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Make Copilot and Codex host detection exclusive in runtime output routing
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add Copilot debt command validation with a pull request acceptance checklist
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Removed PR template
* Drop tautological copilot command-form test
The namespaced-form assertion built '/ponytail:ponytail-debt' from two
constants and compared it to itself — it tests string concatenation, not
wiring. The file-exists check above already catches a renamed manifest.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat: refine ruleset from a full-project field review
A reviewer ran ponytail across a 9-phase rewrite (protocol, PC app, simulator,
RPi daemon, ESP32 firmware) and flagged three gaps. All three land in SKILL.md
and propagate to AGENTS.md + the rule copies:
- Promote the one-runnable-check rule to a headline ("Lazy code without its
check is unfinished"), enforced as a check-rule-copies invariant.
- Hardware carve-out in "When NOT to be lazy": a real device is never the spec
ideal (clock drift, sensor offset), leave the calibration knob.
- Clarify the Output rule: explanation the user explicitly asked for is not
debt, only unrequested prose is.
Fallback instructions kept in sync. Rule-copy check + tests green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: add a behavior gate proving the refinements actually fire
The refinements were verified as injected text, but injected != behavioral.
This adds a behavior eval that probes each refined rule on a task that should
trigger it:
- hardware -> does the output leave a calibration knob?
- explanation -> when a write-up is explicitly requested, is it given in full?
- onecheck -> is a runnable check left behind?
benchmarks/behavior.yaml runs the probes (baseline vs ponytail arm); the
grader benchmarks/behavior.js is proven by tests/behavior.test.js (8 cases,
RED/GREEN, no API key, runs in CI). Live-confirmed: the model under the
current ruleset passes all three gates, graded by the same grader.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ponytail-activate.js and ponytail-runtime.js hardcoded ~/.claude for the
flag file and settings lookup, ignoring CLAUDE_CONFIG_DIR. Add a shared
getClaudeDir() to ponytail-config.js and use it in both. Regression test
added to hooks.test.js.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
On Windows the lifecycle hooks run via PowerShell, which does not expand
cmd.exe-style %CLAUDE_PLUGIN_ROOT%. The path was passed literally, so the hook
launcher could not find the script and both SessionStart and UserPromptSubmit
failed with exit code 1 (issue #19). Switch the two commandWindows entries to
$env:CLAUDE_PLUGIN_ROOT, keeping the working node + .js invocation.
Add a regression test that rejects cmd.exe %VAR% syntax in commandWindows and
asserts every hook command points at a script that actually ships in hooks/.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
hooks/hooks.json used ${PLUGIN_ROOT}, which Claude Code never defines, so the literal resolved against the hook process cwd and SessionStart/UserPromptSubmit failed with 'Cannot find module'. Switch to ${CLAUDE_PLUGIN_ROOT} (and %CLAUDE_PLUGIN_ROOT% for the Codex commandWindows variant); Codex aliases CLAUDE_PLUGIN_ROOT so both hosts resolve. Drop the duplicate inline hooks block from .claude-plugin/plugin.json so hooks load from a single canonical source.
filterSkillBodyForMode only filters lines whose label is a real mode (lite/full/ultra). Rule bullets like 'No unrequested abstractions:' and the 'ponytail:' comment convention were being stripped from injected instructions in every mode. Adds regression test.
Hardening per the A-F benchmark brief: non-trivial logic leaves one
runnable check; ponytail: comments on ceiling-bearing shortcuts name
the ceiling and upgrade path; prefer the edge-case-correct stdlib
option at equal size. Applied to SKILL.md, all cross-agent rule
copies, the hook fallback, and a guard line in ponytail-review.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
v1 lost to caveman on tokens/time despite minimal code: it wrote
essays defending each simplification. v2 caps explanation at three
lines and ships the lazy version instead of stalling on necessity
questions. Benchmark: 136.6k tok vs caveman 138.4k, code 47 vs 117
lines across 5 tasks.
