Skip to content

Commit 9cc41b7

Browse files
garrytanclaude
andauthored
v1.57.6.0 fix wave: 8 community bugs (4 security guards failing open) (garrytan#1911)
* fix(ship): adversarial subagent no longer trips usage-policy denial on own security fixtures (garrytan#1899) The Claude adversarial subagent in /review and /ship was told to "think like an attacker" over the full diff. When the diff includes the repo's own security regression fixtures (real attack payloads, by design), reasoning adversarially over that material triggered Anthropic's real-time usage-policy safeguards and the subagent call was denied — blocking the review. Fix at the prompt's source of truth (scripts/resolvers/review.ts {{ADVERSARIAL_STEP}}): - Authorized-defensive-testing framing: declares this is the maintainer's own repo and that attack-pattern strings inside test/fixture paths are the project's own regression corpus to analyze, not material to expand on. - Fixture summary-mode diff: full content for non-fixture source, --stat/--name-status for test/fixture files, so raw exploit bytes aren't fed into adversarial reasoning. The subagent must state fixtures were reviewed in summary mode (no silent coverage cut). Reported by @bmajewski. Regenerated review/SKILL.md + ship/sections/adversarial.md. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(redact): detect modern sk-proj-/sk-svcacct-/sk-admin- OpenAI keys (garrytan#1868) openai.key (HIGH/block) used /\b(sk-(?:proj-)?[A-Za-z0-9]{32,})\b/, which stops at the first - or _ in the body. Modern OpenAI project/service-account/admin keys use base64url bodies containing - and _, so they never reached the 32-char run and produced ZERO findings — a HIGH credential failing open through /spec, /ship, /cso, and /document-*. Replace with explicit alternation, bare vs prefixed (not a globally-optional prefix, which would match malformed sk--... or separator-less sk-projabc...): sk-{proj,svcacct,admin}- + [A-Za-z0-9_-]{20,} | sk-[A-Za-z0-9]{32,} (legacy) Tests: the three previously-missed shapes now block; FP guards pin that hyphenated prose and malformed sk- strings do NOT match (HIGH tier blocks, so calibration matters). Reported by @jbetala7. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(redact): reject malformed --max-bytes instead of silently disabling the size guard (garrytan#1824) The oversize check is designed to fail CLOSED, but a malformed --max-bytes turned it fail-OPEN. bin/gstack-redact did parseInt(maxBytes,10) and passed it straight through; parseInt("foo") is NaN. The engine guarded with `opts.maxBytes ?? DEFAULT`, and ?? does not catch NaN, so `byteLen > NaN` was always false and the fail-closed block never fired. A negative value made `byteLen > -5` always true, blocking everything. Two layers: - bin/gstack-redact validates the RAW string (parseInt accepts "123abc"->123, "1.5"->1): require /^\d+$/ and > 0, else exit 1 with a clear message. - lib/redact-engine.ts hardens the fallback to Number.isFinite && > 0 else the default cap — a guardrail so the engine never silently runs uncapped even if a bad value reaches it directly. Tests: NaN and negative both fall back to the default cap (oversize still blocks); CLI rejects garbage/negative with exit 1. Reported by @jbetala7. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(learnings): cross-project trust gate is an allowlist, not a denylist (garrytan#1745) gstack-learnings-search --cross-project is documented as an allowlist — foreign learnings load only when user-stated/trusted, to stop one project's AI-generated learnings from injecting into another project's reviews. It was implemented as a denylist: `if (isCrossProject && e.trusted === false) continue`. Any row where `trusted` is missing/undefined (legacy rows from before the field existed, hand-edited rows, rows from other tools) passed `undefined === false` → false → admitted. Those rows leaked across projects. Flip to `e.trusted !== true`. Test: a foreign row with no `trusted` field is now excluded (true still included, false still excluded). Reported by @jbetala7. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(safety): one-way-door classifier catches "rotate ... password" (garrytan#1839) scripts/one-way-doors.ts is the secondary safety net for ad-hoc AskUserQuestion ids with no registry entry; a false negative auto-approves a destructive op. The revoke and reset credential patterns both include `password`, but the rotate pattern omitted it, so the most common phrasing ("rotate the database password") classified as a reversible two-way question. Add `password` to the rotate alternation so all three verbs are parallel. New test covers rotate+password, the revoke/reset/rotate parallel, and rotate's other nouns. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(review): route .mjs/.cjs/.mts/.cts changes to the backend reviewer (garrytan#1810) gstack-diff-scope backend detection matched only *.ts|*.js. Modern Node ships backend code as ESM (.mjs) / CommonJS (.cjs) and explicit-module TS (.mts/.cts); none matched any category, so a PR touching only those files reported no backend scope and the Review Army skipped the backend reviewer. Add the four module extensions to the backend case. Test covers all four. Reported by @jbetala7. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(brain-cache): loadMeta tolerates malformed _meta.json without crashing (garrytan#1879) loadMeta returned the parsed JSON verbatim. A valid JSON file that lacked the last_refresh map made three consumers (isStale, cmdInvalidate, refreshEntity) throw a TypeError dereferencing meta.last_refresh — the sibling last_attempt was already guarded, last_refresh wasn't. Fix in loadMeta: - Shape-guard: JSON.parse can return null/array/string/number; non-object → fresh meta. - Normalize ONLY the dereferenced maps (last_refresh, last_attempt). - Deliberately do NOT default schema_version/endpoint_hash. Leaving them absent makes schemaVersionMismatch()/endpointSwitched() force a rebuild (missing identity = mismatch = safe); defaulting them would suppress cache invalidation and trust a stale file of unknown provenance. Tests: missing last_refresh no longer throws; null/array/primitive treated as cold; missing schema_version forces rebuild instead of a trusted warm hit. Reported by @jbetala7. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(skills): anchor guard/freeze/careful hook paths so they survive CC 2.1.162 (garrytan#1871) The PreToolUse frontmatter hooks for guard, freeze, and careful invoked `bash ${CLAUDE_SKILL_DIR}/.../check-*.sh`. Claude Code 2.1.162 no longer populates ${CLAUDE_SKILL_DIR} in the skill-hook execution env, so it expanded to empty and every Edit/Write/Bash ran `bash /...` and errored — breaking the safety skills entirely. Frontmatter hooks run before any skill-body bash, so no runtime-resolved variable can fix this; the command must be a path that's valid at hook time. Anchor to the installed checkout: $HOME/.claude/skills/gstack/{careful,freeze}/bin/check-*.sh, where the scripts actually live. ($HOME is expanded by the hook shell.) Reported by @omariani-howdy. Regenerated the three SKILL.md from templates. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: v1.58.0.0 — fix-wave release notes, VERSION bump, garrytan#1882 TODO CHANGELOG entry for the 8-fix safety wave (garrytan#1899, garrytan#1868, garrytan#1824, garrytan#1745, garrytan#1839, garrytan#1810, garrytan#1879, garrytan#1871). VERSION + package.json to 1.58.0.0 (MINOR — coordinated multi-file safety fixes on top of main's 1.57.3.0). garrytan#1882 filed as the top TODOS.md item (scoped out of this wave per decision; host-config change touching all 52 skills, distinct from the garrytan#1871 hook fix). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(learnings): strip backticks from garrytan#1745 comment inside the bun -e block The garrytan#1745 trust-gate fix added an explanatory comment containing backticks (`=== false`) and the JS block is a double-quoted `bun -e "..."` bash string, so bash command-substituted the backtick contents on every cross-project search — polluting stderr with "command not found" and leaving a latent shell-injection / source-corruption surface in a security gate. Caught by the wave's own adversarial review (garrytan#1899 framing working as intended). Reworded the comments to avoid backticks and dollar-paren entirely; the gate logic is unchanged. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(golden): refresh ship golden baselines (garrytan#1899 prompt + main's PR-title line) The three ship golden fixtures were stale: main's v1.57.3.0 added the always-loaded PR-title invariant to ship/SKILL.md but did not regenerate the goldens (the golden regression test fails on main too), and the codex golden still carried an unresolved ${ctx.paths.binDir} token. Regenerated from the current generated ship skills, which also picks up this wave's garrytan#1899 adversarial-prompt framing (inlined for codex/factory). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
1 parent 45cc95d commit 9cc41b7

26 files changed

Lines changed: 364 additions & 27 deletions

CHANGELOG.md

Lines changed: 89 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,94 @@
11
# Changelog
22

3+
## [1.57.6.0] - 2026-06-07
4+
5+
## **Eight community-filed bugs fixed in one wave, four of them security guards that were quietly failing open.**
6+
## **Your redaction gate now catches modern OpenAI keys, and `/ship`'s adversarial review stops choking on your own security tests.**
7+
8+
This is a fix wave. The throughline: guards that reported success while doing nothing.
9+
The secret-redaction gate that every `/spec`, `/ship`, `/cso`, and `/document-*` run
10+
passes through was blind to modern `sk-proj-`/`sk-svcacct-`/`sk-admin-` OpenAI keys and
11+
silently dropped its size cap on a bad flag. The cross-project learnings trust gate was
12+
an allowlist on paper and a denylist in code, so untrusted rows leaked between projects.
13+
The destructive-action classifier waved through "rotate the database password." Each one
14+
looked like it was protecting you. None of them were. All four now fail closed, with
15+
tests that pin the exact case that used to slip by. Three more fixes clear silent
16+
crashes and skipped reviewers, and `/ship`'s adversarial pass no longer trips Anthropic's
17+
usage policy when it reads your repo's own attack-payload fixtures.
18+
19+
### The numbers that matter
20+
21+
Reproduce with `bun test test/redact-engine.test.ts test/gstack-learnings-search.test.ts test/one-way-doors.test.ts test/diff-scope.test.ts test/brain-cache-roundtrip.test.ts`.
22+
23+
| Guard / path | Before | After |
24+
|---|---|---|
25+
| `sk-proj-`/`sk-svcacct-`/`sk-admin-` OpenAI keys | zero findings (HIGH fails open) | blocked, with prose false-positive guards |
26+
| `gstack-redact --max-bytes <garbage>` | NaN silently disables the size cap | rejected at the CLI; engine backstop holds |
27+
| Cross-project learnings with no `trusted` field | imported (denylist bug) | excluded (true allowlist) |
28+
| "rotate the database password" | classified two-way (auto-approvable) | classified one-way (always asks) |
29+
| `.mjs/.cjs/.mts/.cts`-only PRs | backend reviewer skipped | backend reviewer runs |
30+
| `_meta.json` missing `last_refresh` | brain-cache crashes (TypeError) | degrades to a cold cache |
31+
| Safety-skill hooks on Claude Code 2.1.162 | every Edit/Write errored | hooks resolve and run |
32+
| `/ship` adversarial review over security fixtures | denied by usage policy | runs, fixtures read in summary mode |
33+
34+
The redaction one is the sharpest: a project/service-account/admin OpenAI key pasted
35+
into a spec or PR body used to sail straight through the gate. Now it blocks, and the
36+
calibration is pinned so hyphenated prose like "the sk-learning-rate schedule" does not
37+
false-positive and wedge your ship.
38+
39+
### What this means for you
40+
41+
If you rely on the redaction guard or the cross-project learnings gate, they now do what
42+
the docs always said. If you run `/ship` on a repo that tests its own security guards,
43+
adversarial review stops dying on contact with your fixtures. And if you are on Claude
44+
Code 2.1.162, `/guard`, `/freeze`, and `/careful` work again instead of erroring on every
45+
edit. Upgrade and re-run anything that touched these paths.
46+
47+
### Itemized changes
48+
49+
#### Fixed
50+
- **Redaction misses modern OpenAI keys (#1868).** `openai.key` (HIGH/block) used a
51+
contiguous-alphanumeric pattern that stopped at the first `-`/`_`, so base64url-bodied
52+
`sk-proj-`/`sk-svcacct-`/`sk-admin-` keys produced no finding and failed open through
53+
every redaction sink. Replaced with explicit bare-vs-prefixed alternation; added
54+
positive and false-positive tests. Reported by @jbetala7.
55+
- **Redaction size cap fails open on a bad flag (#1824).** A malformed `--max-bytes`
56+
parsed to `NaN`, and `byteLen > NaN` is always false, silently disabling the
57+
fail-closed oversize guard; a negative value blocked everything. The CLI now rejects
58+
non-integer / non-positive values, and the engine falls back to the default cap as a
59+
backstop. Reported by @jbetala7.
60+
- **Cross-project learnings trust gate leaked (#1745).** `gstack-learnings-search
61+
--cross-project` is documented as an allowlist but was coded as `trusted === false`,
62+
admitting any row missing the `trusted` field. Flipped to `trusted !== true`. Reported
63+
by @jbetala7.
64+
- **Destructive-action classifier missed "rotate ... password" (#1839).** The `rotate`
65+
keyword pattern omitted `password` while its `revoke`/`reset` siblings included it, so
66+
the most common credential-rotation phrasing classified as a reversible two-way
67+
question. Added `password` to the alternation.
68+
- **Review Army skipped backend reviewer on ESM/CJS PRs (#1810).** `gstack-diff-scope`
69+
matched only `*.ts|*.js`; a PR touching only `.mjs/.cjs/.mts/.cts` reported no backend
70+
scope. Added the four module extensions. Reported by @jbetala7.
71+
- **Brain-cache crash on a partial `_meta.json` (#1879).** `loadMeta` returned parsed
72+
JSON verbatim; a file missing `last_refresh` crashed three consumers with a TypeError.
73+
Added an object-shape guard and map normalization; missing schema/endpoint identity now
74+
forces a safe rebuild rather than trusting a stale file. Reported by @jbetala7.
75+
- **Safety-skill hooks broken on Claude Code 2.1.162 (#1871).** `guard`, `freeze`, and
76+
`careful` frontmatter hooks used `${CLAUDE_SKILL_DIR}`, which CC 2.1.162 no longer
77+
populates, so every Edit/Write/Bash errored. Anchored the hook commands to the
78+
installed checkout path. Reported by @omariani-howdy.
79+
- **`/ship` adversarial review denied on own security fixtures (#1899).** The Claude
80+
adversarial subagent reasoned "like an attacker" over the full diff; when the diff
81+
included the repo's own attack-payload regression fixtures, Anthropic's real-time
82+
usage-policy safeguards denied the call. The subagent now carries authorized-defensive
83+
-testing framing and reads fixture/test files in summary mode (no raw payload bytes),
84+
stating so explicitly. Reported by @bmajewski.
85+
86+
#### For contributors
87+
- `#1882` (skills hardcode `~/.claude/skills/gstack/`, breaking non-`gstack` install
88+
dirs) is filed as the top item in `TODOS.md`. It was scoped out of this wave once it
89+
proved to be a host-config/preamble change touching all 52 skills, distinct from the
90+
`#1871` hook fix it was originally paired with.
91+
392
## [1.57.5.0] - 2026-06-07
493

594
## **Your agent now keeps its decisions, not just its code.**

TODOS.md

Lines changed: 43 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,48 @@
11
# TODOS
22

3+
## NEXT PRIORITY
4+
5+
### P1: #1882 — portable skill-install prefix (non-`gstack` install dirs break silently)
6+
7+
**What:** Every generated SKILL.md hardcodes the literal `~/.claude/skills/gstack/...`
8+
for its `bin/`/asset calls (the per-invocation telemetry/config preamble plus ~9
9+
resolvers). `setup` wires the top-level skill symlinks for any directory name, so
10+
installing at `~/.claude/skills/<other>` leaves every internal `bin` reference
11+
pointing at a non-existent `~/.claude/skills/gstack/` path — failing **silently, at
12+
skill-invocation time**. Make the emitted references portable: resolve the install
13+
root at runtime (the preamble already defines `GSTACK_ROOT`/`GSTACK_BIN` in
14+
`scripts/resolvers/preamble/generate-preamble-bash.ts` but the literals don't use
15+
them) and emit `$GSTACK_BIN`-relative paths instead of the hardcoded prefix.
16+
17+
**Why:** Filed as #1882. Split out of the June 2026 fix wave (decision A) once
18+
implementation showed it is a host-config/design change, not a fix-wave patch. The
19+
urgent half — the guard/freeze/careful frontmatter hooks broken on CC 2.1.162 — was
20+
already fixed in that wave (#1871) with a literal `$HOME`-anchored path, because
21+
frontmatter hooks run before any runtime variable exists and cannot use `$GSTACK_BIN`.
22+
So #1882 is now purely the body-preamble portability work.
23+
24+
**Pros:** Unblocks installs at any directory name; removes a whole class of silent
25+
invocation-time failures.
26+
**Cons:** Touches the most load-bearing bash in the repo (every skill's preamble);
27+
a silent mistake breaks all 52 skills. High blast radius — needs its own focused PR.
28+
29+
**Context / where to start:**
30+
- Rewire `ctx.paths.binDir` (and browse/design dir paths) + the ~9 resolvers that
31+
emit the literal (`testing.ts`, `review.ts`, `design.ts`, `browse.ts`,
32+
`redact-doc.ts`, `tasks-section.ts`, `preamble/generate-*.ts`) to use the
33+
preamble-defined `$GSTACK_ROOT`/`$GSTACK_BIN`.
34+
- Ensure `GSTACK_ROOT`/`GSTACK_BIN` are defined before first use in EVERY skill's
35+
preamble (verify the telemetry preamble's first bin call is after the definition).
36+
- **Test conflict (verified):** `test/gen-skill-docs.test.ts:1942` and the sibling
37+
ship assertion currently *assert* generated Claude output `.toContain('~/.claude/skills/gstack')`
38+
as a guardrail that Codex-host paths don't leak. These must be rewritten to match
39+
the new portable scheme.
40+
- Regenerate all 52 SKILL.md (`bun run scripts/gen-skill-docs.ts --host all`); never
41+
hand-edit generated files. Bisect: resolver/host-config change commit, then the
42+
52-file regen commit.
43+
- Smoke-test a skill invocation from a non-`gstack` install dir to prove the fix.
44+
- Sibling of #349 (the `$CLAUDE_CONFIG_DIR` / `~/.claude` path issue).
45+
346
## Test infrastructure
447

548
### ✅ DONE (v1.53.1.0): Rebaseline parity-suite (v1.44.1 → v1.53.0.0)

VERSION

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
1.57.5.0
1+
1.57.6.0

bin/gstack-brain-cache

Lines changed: 17 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -83,7 +83,23 @@ function loadMeta(scope: 'cross-project' | 'per-project', projectSlug: string |
8383
return { schema_version: GSTACK_SCHEMA_PACK_VERSION, endpoint_hash: detectEndpointHash(), last_refresh: {}, last_attempt: {} };
8484
}
8585
try {
86-
return JSON.parse(readFileSync(path, 'utf-8')) as CacheMeta;
86+
const parsed = JSON.parse(readFileSync(path, 'utf-8')) as unknown;
87+
// #1879: a valid JSON file can still be the wrong shape. JSON.parse can return
88+
// null/array/string/number, and a partial object can omit last_refresh — three
89+
// consumers (isStale, cmdInvalidate, refreshEntity) dereference meta.last_refresh
90+
// unguarded and crash with a TypeError.
91+
if (typeof parsed !== 'object' || parsed === null || Array.isArray(parsed)) {
92+
return { schema_version: GSTACK_SCHEMA_PACK_VERSION, endpoint_hash: detectEndpointHash(), last_refresh: {}, last_attempt: {} };
93+
}
94+
const meta = parsed as CacheMeta;
95+
// Normalize ONLY the dereferenced maps. Do NOT default schema_version /
96+
// endpoint_hash — leaving them absent makes schemaVersionMismatch() /
97+
// endpointSwitched() correctly force a rebuild (missing identity = mismatch =
98+
// safe). Defaulting them to current values would suppress invalidation and
99+
// trust a stale file of unknown provenance.
100+
meta.last_refresh = meta.last_refresh ?? {};
101+
meta.last_attempt = meta.last_attempt ?? {};
102+
return meta;
87103
} catch {
88104
// Corrupt _meta — start fresh (entries will refresh on next access).
89105
return { schema_version: GSTACK_SCHEMA_PACK_VERSION, endpoint_hash: detectEndpointHash(), last_refresh: {}, last_attempt: {} };

bin/gstack-diff-scope

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -75,7 +75,10 @@ while IFS= read -r f; do
7575

7676
# Backend: everything else that's code (excluding views/components already matched)
7777
*.rb|*.py|*.go|*.rs|*.java|*.php|*.ex|*.exs) BACKEND=true ;;
78-
*.ts|*.js) BACKEND=true ;; # Non-component TS/JS is backend
78+
# Non-component TS/JS is backend. Include ESM/CJS (.mjs/.cjs) and
79+
# explicit-module TS (.mts/.cts) — #1810: these matched no category, so an
80+
# ESM/CJS-only PR skipped the backend reviewer entirely.
81+
*.ts|*.js|*.mjs|*.cjs|*.mts|*.cts) BACKEND=true ;;
7982
esac
8083
done <<< "$FILES"
8184

bin/gstack-learnings-search

Lines changed: 8 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -90,10 +90,16 @@ for (const taggedLine of lines) {
9090
const isCrossProject = sourceTag === 'cross';
9191
e._crossProject = isCrossProject;
9292
93-
// Trust gate: cross-project learnings only loaded if trusted (user-stated)
93+
// Trust gate: cross-project learnings only loaded if trusted (user-stated).
9494
// This prevents prompt injection from one project's AI-generated learnings
9595
// silently influencing reviews in another project.
96-
if (isCrossProject && e.trusted === false) continue;
96+
// #1745: this is an ALLOWLIST, not a denylist. The old equals-false check
97+
// admitted any row where trusted is missing/undefined (legacy rows written
98+
// before the field existed, hand-edited rows, rows from other tools).
99+
// Require trusted to be exactly true. NOTE: this whole block is a
100+
// double-quoted bun -e string, so bash still does command substitution
101+
// inside it. Keep backticks and dollar-paren out of these comments.
102+
if (isCrossProject && e.trusted !== true) continue;
97103
98104
entries.push(e);
99105
} catch {}

bin/gstack-redact

Lines changed: 14 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -161,12 +161,25 @@ function readLines(path: string | undefined): string[] | undefined {
161161
function buildOpts(): ScanOptions {
162162
const vis = (arg("--repo-visibility") as RepoVisibility) || "unknown";
163163
const maxBytes = arg("--max-bytes");
164+
// #1824: validate the RAW string, not the parse result. parseInt("123abc")
165+
// is 123 and parseInt("foo") is NaN — both silently corrupt the fail-closed
166+
// oversize guard. Require a clean positive integer or reject before scanning.
167+
let maxBytesOpt: number | undefined;
168+
if (maxBytes !== undefined) {
169+
if (!/^\d+$/.test(maxBytes) || Number(maxBytes) <= 0) {
170+
process.stderr.write(
171+
`gstack-redact: --max-bytes must be a positive integer (got "${maxBytes}")\n`,
172+
);
173+
process.exit(1);
174+
}
175+
maxBytesOpt = Number(maxBytes);
176+
}
164177
return {
165178
repoVisibility: ["public", "private", "unknown"].includes(vis) ? vis : "unknown",
166179
allowlist: readLines(arg("--allowlist")),
167180
selfEmail: arg("--self-email"),
168181
repoPublicEmails: readLines(arg("--repo-public-emails")),
169-
...(maxBytes ? { maxBytes: parseInt(maxBytes, 10) } : {}),
182+
...(maxBytesOpt !== undefined ? { maxBytes: maxBytesOpt } : {}),
170183
};
171184
}
172185

careful/SKILL.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ hooks:
1414
- matcher: "Bash"
1515
hooks:
1616
- type: command
17-
command: "bash ${CLAUDE_SKILL_DIR}/bin/check-careful.sh"
17+
command: "bash $HOME/.claude/skills/gstack/careful/bin/check-careful.sh"
1818
statusMessage: "Checking for destructive commands..."
1919
---
2020
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->

careful/SKILL.md.tmpl

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ hooks:
1919
- matcher: "Bash"
2020
hooks:
2121
- type: command
22-
command: "bash ${CLAUDE_SKILL_DIR}/bin/check-careful.sh"
22+
command: "bash $HOME/.claude/skills/gstack/careful/bin/check-careful.sh"
2323
statusMessage: "Checking for destructive commands..."
2424
sensitive: true
2525
---

freeze/SKILL.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -15,12 +15,12 @@ hooks:
1515
- matcher: "Edit"
1616
hooks:
1717
- type: command
18-
command: "bash ${CLAUDE_SKILL_DIR}/bin/check-freeze.sh"
18+
command: "bash $HOME/.claude/skills/gstack/freeze/bin/check-freeze.sh"
1919
statusMessage: "Checking freeze boundary..."
2020
- matcher: "Write"
2121
hooks:
2222
- type: command
23-
command: "bash ${CLAUDE_SKILL_DIR}/bin/check-freeze.sh"
23+
command: "bash $HOME/.claude/skills/gstack/freeze/bin/check-freeze.sh"
2424
statusMessage: "Checking freeze boundary..."
2525
---
2626
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->

0 commit comments

Comments
 (0)