Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cyanheads/git-mcp-server --skill report-issuegit clone --depth 1 https://github.com/cyanheads/git-mcp-serverWrote 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/cyanheads/git-mcp-server/report-issue)<a href="https://agentmods.dev/skills/cyanheads/git-mcp-server/report-issue"><img src="https://agentmods.dev/badge/skills/cyanheads/git-mcp-server/report-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.
<a href="https://agentmods.dev/skills/cyanheads/git-mcp-server/report-issue"><img src="https://agentmods.dev/badge/skills/cyanheads/git-mcp-server/report-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 69 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.
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 | $0.00051 | $0.02460 |
| Opus 5.5 | $0.00020 | $0.00984 |
| Sonnet 5.5 | $0.00010 | $0.00492 |
| Haiku 4.5 | $0.00005 | $0.00246 |
Grade A, and why
report-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 1mo 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Typical triggers:
- A git tool handler returns wrong results or throws on valid input
- A git provider (
CliGitProvider) fails or misbehaves — wrong output parsing, error transformation, timeout handling - Transport bugs — HTTP (Hono + Streamable HTTP), stdio, SSE framing, session handling
- Auth bugs — JWT / OAuth / scope enforcement
- Storage backend misbehaves — in-memory, filesystem, supabase, cloudflare
- Domain logic errors — wrong git output, missing edge cases, bad state transitions
- Resource handlers return stale, incomplete, or incorrect data
- Missing or incorrect
.describe()on schema fields causing poor LLM tool use - Feature requests — new git operations, verbosity levels, response fields, auth strategies, storage providers
For general gh CLI workflows outside issue filing (PRs, workflows, API access), see the github-cli skill.
Before Filing
-
Confirm the repo:
gh repo view --json nameWithOwner -q '.nameWithOwner'Should output
cyanheads/git-mcp-server. -
Search existing issues:
gh issue list --search "your error message or keyword" -
Reproduce the issue — confirm it's reproducible. Note the exact input, transport mode (stdio/http), git provider (cli), and any relevant env vars (
GIT_SIGN_COMMITS,GIT_BASE_DIR,STORAGE_PROVIDER_TYPE, etc.). -
Check logs — review server output and, if running HTTP, the response body for structured error details (
McpErrorcode + context). -
Capture versions —
bun pm ls @cyanheads/git-mcp-server,bun --version,git --version, OS version.
Writing Well-Structured Issues
Good issues are scannable, concrete, and self-contained. These patterns apply to both bugs and features — the guidance targets any prose block (Description, Additional context, feature proposals).
- Lead with specifics. Name the tool, provider, resource, or symptom. "Currently
git_mergethrowsMcpError(INTERNAL_ERROR)on a CONFLICT exit instead of returning{conflicts: true}" beats "Merge is broken." A reader should know what's wrong before the end of the first sentence. - Embed library/service links on first mention.
[Hono](https://hono.dev/),[tsyringe](https://github.com/microsoft/tsyringe),[jose](https://github.com/panva/jose). Link to the canonical repo so readers can verify the dependency and reach docs in one click. - Use
owner/repo#Nfor cross-repo issue references. GitHub auto-renders them as linked references (e.g.cyanheads/mcp-ts-template#46). Bare#Nonly works for same-repo issues. - Add a
Related: #Nline near the top when the issue grows from prior context (discussions, other issues, PRs). Makes provenance clickable. - Lead design sections with a philosophy sentence. Bold a short principle before the tradeoff details — e.g. "Philosophy: conflicts are a structured success, not an error." Establishes the lens for the rest of the section.
- Prefer Markdown tables for comparisons. When showing options, strategies, or tradeoffs — tables are the highest-density format for scanning N rows × M attributes.
- Separate
### Scopefrom### Out of scope. The latter is as important as the former — it pre-empts scope-creep debates in comments and signals you've thought about the boundaries. - Use
Depends on: owner/repo#Nto declare ordering explicitly when implementation is blocked on another issue landing first. - Skip collaborator-framing sign-offs. Lines like "Happy to open a PR", "let me know if you'd like", "willing to contribute" read as noise. A PR link beats an offer; if you're the maintainer filing against your own repo, the offer is redundant. End the body at the last substantive point.
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.
- 1mo ago First seen · 250 lines · 51 tokens per session scan A 0a1068728087
report-issue is a skill published in the GitHub repository cyanheads/git-mcp-server (242 stars, last pushed 24d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,460 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
papi-build
Invoke when executing a build via buildexecute. Covers branching, gestalt pre-build check, and post-build audit.
papi-auto
Continue an approved PAPI cycle through implementation, verification and review using bounded autonomy. Resume durable work without rebuilding it; propose new scope before persisting it.
gitlab-discovery
Find a GitLab project or namespace and establish the exact target for follow-up repository, merge request, work-item or CI work. Use for GitLab project discovery, not local filesystem search or GitHub repositories.
reviewing-sla-definitions
Reviewing ServiceNow SLA, OLA and underpinning-contract definitions and how they perform: breach rates per definition, overlapping or duplicated definitions on the same table and target, and definitions that never attach. Use when the user asks about SLA breaches by definition, too many SLAs, duplicate or conflicting…
split-to-prs
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.