meta-mcp: Skill for Claude Code

.claude/skills/meta-mcp-fix-issue/SKILL.md

meta-mcp-fix-issue is a skill for Claude Code from exileum/meta-mcp. It costs 133 tokens per session (2,907 once invoked), scanned A, original, MIT.

A step-by-step workflow for fixing GitHub issues in the meta-mcp project. GitHub issues are tracked reports or requests, and a feature branch is a separate line of code for making a change safely.

In plain words
What is it for?
Use it to fetch one or more issues, plan and implement their fixes, run tests, update project files, open a detailed pull request, and respond to review-bot comments.
Why use it?
It organizes the work from understanding the issue through testing, documentation, pull-request creation, and review feedback. This helps avoid missed project updates during a fix.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the ExitPlanMode tool.

This is exileum/meta-mcp's own configuration. It tells Claude Code how to work on meta-mcp 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 meta-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to exileum/meta-mcp. 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/exileum/meta-mcp/main/.claude/skills/meta-mcp-fix-issue/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/exileum/meta-mcp

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 meta-mcp-fix-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/exileum/meta-mcp/meta-mcp-fix-issue/github.svg)](https://agentmods.dev/skills/exileum/meta-mcp/meta-mcp-fix-issue)
Your own site
<a href="https://agentmods.dev/skills/exileum/meta-mcp/meta-mcp-fix-issue"><img src="https://agentmods.dev/badge/skills/exileum/meta-mcp/meta-mcp-fix-issue/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.

agentmods 80×15 button for meta-mcp-fix-issue

Your own site · 80×15
<a href="https://agentmods.dev/skills/exileum/meta-mcp/meta-mcp-fix-issue"><img src="https://agentmods.dev/badge/skills/exileum/meta-mcp/meta-mcp-fix-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00133 $0.02907
Opus 5 $0.00067 $0.01453
Sonnet 5 $0.00027 $0.00581
Haiku 4.5 $0.00013 $0.00291

Measured 11d ago against content hash a09b16d88502, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

meta-mcp-fix-issue 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 11d 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.

.claude/skills/meta-mcp-fix-issue/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix GitHub Issue(s)

You are fixing GitHub issue(s) $ARGUMENTS in the meta-mcp project.

Parse the arguments: split $ARGUMENTS by spaces, commas, or other separators. Each token may be a bare number (42), a hash-prefixed number (#42), or a full GitHub issue URL. Extract all issue numbers into a list. If no argument is provided, ask the user for the issue number(s).

Single vs. multi-issue mode: if there is only one issue, follow the standard single-issue flow below. If there are multiple issues, follow the multi-issue adaptations noted in each step — all issues are fixed together in one branch, one combined PR.

This workflow works best with extended thinking enabled — complex issues benefit from deep reasoning about root causes and fix strategies.

Step 1: Gather Context

Create tasks to track progress throughout this workflow.

  1. Switch to main and update — always start from the latest main:
    git checkout main
    git pull
    
  2. Fetch the issue(s) via gh issue view <number> --json title,body,labels,state,milestone — run for each issue number.
  3. Read all issues carefully — understand each problem, affected files, severity, and any proposed solutions. In multi-issue mode, note overlaps and shared affected areas.
  4. Check if already fixed — for each issue, before exploring code, read CHANGELOG.md (especially the [Unreleased] section and recent releases) and search for references to the issue number (#<number>) or related keywords. When working through a large backlog of issues, earlier fixes may have already resolved or partially addressed some issues. If an issue is already fixed, drop it from the list and inform the user. If ALL issues are already fixed, close the workflow early.
  5. Explore the codebase — read the files mentioned across all issues. Use the Grep and Glob tools (not bash grep/find) to search efficiently.
  6. Verify with official documentation — if any issue references or implies external APIs, specs, or platform behavior (e.g., anything about Instagram API, Threads API, Meta Graph API), proactively look up the official documentation using WebSearch / WebFetch. Don't wait for the issue to provide links — if the fix touches API endpoints, parameters, or platform-specific behavior, always verify against the source of truth.
  7. Check compatibility (multi-issue only) — if two issues propose conflicting changes to the same code, flag this to the user via AskUserQuestion and suggest splitting them into separate PRs.
  8. Summarize findings to the user: for each issue — what's broken, what the fix should look like, and what files need changes. In multi-issue mode, highlight shared files and any interactions between fixes.

Read the full file on GitHub · 171 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. 11d ago First seen · 171 lines · 133 tokens per session scan A a09b16d88502

Subscribe to this mod's changes

meta-mcp-fix-issue is a skill published in the GitHub repository exileum/meta-mcp (12 stars, last pushed yesterday), licensed MIT. It adds 133 tokens to every session and 2,907 once invoked, about $0.0007 per session on Opus 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 2026-08-30.

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

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

comet-github-issue-fix

A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.

rpamis/comet · 71 tokens

auto-repo-setup

Diagnose, repair, and standardize repository setup and safe Git workflows for Claude Code or Codex. Use when a repository will not run, a collaborator is onboarding, dependencies or credentials are missing, the user wants startup sync, SessionStart output is duplicated, project instructions or hooks need auditing, or…

daymade/claude-code-skills · 112 tokens