llms: Skill for Claude Code

.claude/skills/pr-fix/SKILL.md

pr-fix is a skill for Claude Code from matteocervelli/llms. It costs 49 tokens per session (2,138 once invoked), scanned C, original, MIT.

A pull-request preparation workflow that checks whether a proposed code change can be merged, investigates CI failures and review comments, and fixes problems before handoff.

In plain words
What is it for?
Use it to inspect, repair, and validate a pull request before merging it.
Why use it?
It gathers the common reasons a pull request is blocked in one triage process instead of making you check merge conflicts, automated checks, reviews, and bot feedback separately.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is matteocervelli/llms's own configuration. It tells Claude Code how to work on llms itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llms configures →

Reuse

Borrowing it

Nothing to install: this file belongs to matteocervelli/llms. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/matteocervelli/llms/main/.claude/skills/pr-fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/matteocervelli/llms

Made for: Claude Code.

Wrote 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.

agentmods badge for pr-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteocervelli/llms/pr-fix.svg)](https://agentmods.dev/skills/matteocervelli/llms/pr-fix)
Your own site
<a href="https://agentmods.dev/skills/matteocervelli/llms/pr-fix"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/pr-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.02138
Opus 5 $0.00024 $0.01069
Sonnet 5 $0.00010 $0.00428
Haiku 4.5 $0.00005 $0.00214

Measured 3d ago against content hash 103c89ea50ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

pr-fix scanned grade C with 2 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf node_modules package-lock.json || rm -rf __pycache__ .pytest_cache

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

RESULT=$(curl -s \
.claude/skills/pr-fix/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Fix Skill

Purpose

Full triage, fix, and pre-flight for a PR. Diagnoses all issues (merge conflicts, CI failures, bot comments, review requests), fixes them, enforces /pre-commit before pushing, then hands off to /pr-merge for the actual merge and post-merge workflow.

Usage

/pr-fix <pr-number>

Relationship with other skills:

  • /pr-fix = triage problems + fix them + pre-flight validation (you stay on the PR branch)
  • /pr-merge = validate readiness + execute merge + post-merge workflow (docs, milestone, release)
  • Use /pr-fix first when you know there are issues. Use /pr-merge when you expect the PR is ready.

Phase 1: Full Triage

Checkout the PR branch first:

gh pr checkout <pr-number>

Then run ALL four sources in parallel:

REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)
PR=<pr-number>

# 1. PR metadata — mergeability, draft state, review decision
gh pr view $PR --json mergeable,isDraft,state,reviewDecision,additions,deletions

# 2. CI check status
gh pr checks $PR --repo $REPO

# 3. Bot inline comments (Codex, Gemini, etc.)
gh api repos/$REPO/pulls/$PR/comments \
  --jq '.[] | "[\(.path):\(.line // .original_line // "?")]\n\(.body)\n---"'

# 4. Top-level reviews (approval/request-changes state)
gh pr view $PR --repo $REPO --json reviews \
  --jq '.reviews[] | "\(.author.login) [\(.state)]: \(.body)"'

# 5. Forgejo CI status (if dual-remote)
  SHA=$(gh pr view $PR --json headRefOid --jq '.headRefOid')
fi

If bot reviews are still pending, poll until complete (max 3 attempts, 30s apart):

for i in 1 2 3; do
  STATE=$(gh pr checks $PR --repo $REPO 2>&1)
  echo "$STATE"
  echo "$STATE" | grep -q "pending" && sleep 30 || break
done

Phase 2: Triage Decision

Hard Stops — Report and Exit

Condition Action
mergeable: CONFLICTING "Merge conflicts detected. Resolve first: gh api -X PUT repos/O/R/pulls/N/update-branch or rebase locally, then re-run /pr-fix."
isDraft: true "PR is a draft. Mark as ready for review first."
state != OPEN "PR is not open (state: X). Nothing to fix."

Read the full file on GitHub · 265 lines

Changes

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.

  1. 3d ago First seen · 265 lines · 49 tokens per session scan C 103c89ea50ca

Subscribe to this mod's changes

pr-fix is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 2,138 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

NousResearch/hermes-agent · 19 tokens

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

bisect

Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.

chromium/chromium · 52 tokens

mantis-critic

Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.

google/mantis · 55 tokens

hotpath_bump

Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…

pawurb/hotpath-rs · 73 tokens

triaging-merge-queue-failures

Decision procedure for a PR that failed or was removed from the Trunk merge queue: classify the kick (superseded by a newer commit, not mergeable, a gate that failed on a cancelled run, real failure, one-off flake, or repo-wide flaky/infra issue) and take the matching action (wait, hold and fix, requeue once, or…

PostHog/posthog-foss · 180 tokens