Borrowing it
Nothing to install: this file belongs to auerbachb/claude-code-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/skills/fixpr/SKILL.mdgit clone --depth 1 https://github.com/auerbachb/claude-code-configWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/auerbachb/claude-code-config/fixpr)<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/fixpr"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/fixpr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/fixpr"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/fixpr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 287 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 892 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.18354 |
| Opus 5.5 | $0.00035 | $0.07342 |
| Sonnet 5.5 | $0.00018 | $0.03671 |
| Haiku 4.5 | $0.00009 | $0.01835 |
Grade A, and why
fixpr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 872 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bounded-convergence cleanup of the current branch's PR (issue #454 added the post-push review-wait loop to the original single-pass design). After this completes:
- Zero uncollapsed review threads in the browser (all resolved via GraphQL)
- Zero failing CI checks (all fixed and passing)
- Every finding replied to with what was done
- A definitive bot verdict on the final SHA — or an explicit cap-hit report naming what is still pending (never a silent "we pushed, bye" exit)
Portable helper resolution
Resolve the helpers used by executable examples before Step 0. The handoff-path helper has a documented legacy fallback; every write/safety helper is required.
resolve_script() {
local name="$1" candidate
for candidate in \
"$HOME/.claude/skills-worktree/.claude/scripts/$name" \
"$HOME/.claude/scripts/$name" \
".claude/scripts/$name"; do
if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
done
return 1
}
PR_AUTHORSHIP_SH=$(resolve_script pr-authorship.sh || true)
HANDOFF_STATE_SH=$(resolve_script handoff-state.sh || true)
REPLY_THREAD_SH=$(resolve_script reply-thread.sh || true)
RESOLVE_REVIEW_THREADS_SH=$(resolve_script resolve-review-threads.sh || true)
DIFF_SURVIVAL_SH=$(resolve_script diff-survival-check.sh || true)
LOCAL_REVIEW_SH=$(resolve_script local-review.sh || true)
CLEAN_BEHIND_SH=$(resolve_script clean-behind-check.sh || true)
ADMIN_MERGE_SH=$(resolve_script admin-merge.sh || true)
MERGE_GATE_SH=$(resolve_script merge-gate.sh || true)
[[ -n "$PR_AUTHORSHIP_SH" ]] || { echo "ERROR: pr-authorship.sh not found (checked all three paths) — fix workflow authorship gate unavailable" >&2; exit 1; }
[[ -n "$REPLY_THREAD_SH" ]] || { echo "ERROR: reply-thread.sh not found (checked all three paths) — review replies unavailable" >&2; exit 1; }
[[ -n "$RESOLVE_REVIEW_THREADS_SH" ]] || { echo "ERROR: resolve-review-threads.sh not found (checked all three paths) — thread resolution unavailable" >&2; exit 1; }
[[ -n "$DIFF_SURVIVAL_SH" ]] || { echo "ERROR: diff-survival-check.sh not found (checked all three paths) — rebase survival gate unavailable" >&2; exit 1; }
[[ -n "$LOCAL_REVIEW_SH" ]] || { echo "ERROR: local-review.sh not found (checked all three paths) — local review unavailable" >&2; exit 1; }
[[ -n "$CLEAN_BEHIND_SH" ]] || { echo "ERROR: clean-behind-check.sh not found (checked all three paths) — clean-BEHIND verification unavailable" >&2; exit 1; }
[[ -n "$ADMIN_MERGE_SH" ]] || { echo "ERROR: admin-merge.sh not found (checked all three paths) — clean-BEHIND recovery unavailable" >&2; exit 1; }
[[ -n "$MERGE_GATE_SH" ]] || { echo "ERROR: merge-gate.sh not found (checked all three paths) — residual merge verification unavailable" >&2; exit 1; }
if [[ -z "$HANDOFF_STATE_SH" ]]; then
echo "DEGRADED: handoff-state.sh not found (checked all three paths) — namespaced handoff path unavailable, continuing with legacy flat path" >&2
fi
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed · -84 lines 54a01be0f737
- 28d ago Changed 3d593b6297e1
- 29d ago Changed · +12 lines 29f136da94a4
- 1mo ago Changed · +6 lines 026c5ef96ffa
- 1mo ago Changed 0574a479ed00
- 2mo ago First seen · 938 lines · 88 tokens per session scan A 7bedcf36f086
fixpr is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 18,354 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
robin
Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to…
revert
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level. Use when the user asks to 'revert this track', 'undo a phase', 'revert task X', or says 'roll back the last task', 'undo this work'.
upload
Pre-upload gate for track handoff. Verifies review status, HLD approvals, deploy checklist, and validator chain before git upload or PR submission.
bump-version
Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.
kodus-business-rules-validation
Use when the user wants Kodus to validate local diff changes against task requirements, acceptance criteria, or business rules via kodus pr business-validation, especially for implementation-vs-task or merge readiness checks.
Cross-File Leakage リファクタ後の caller 側残骸検出
A code review check for structural changes such as renamed functions, changed arguments, moved files, or split modules. It searches the rest of the project for callers that still use the old structure.