What is gitpin AGENTS.md?

Project instructions for GitPin, a read-only MCP server that finds evidence across multiple Git repositories and ties answers to exact commits, files, lines, and full commit identifiers.

Working on GitPin’s TypeScript source, documentation, client rules, citation format, continuous integration, and evidence checks.

They help a coding assistant use the repository’s documented sources and preserve traceable evidence instead of relying on uncertain summaries.

gitpin AGENTS.md — Instructions file by shmindmaster

Install

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.

agentmods

npx agentmods add instructions/shmindmaster/gitpin/agents-md

Clone the repo

git clone --depth 1 https://github.com/shmindmaster/gitpin

Made for: Codex, OpenCode.

Per session 1,236 This file is loaded in full into every session.

When invoked 1,236 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5	$0.01236	$0.01236
Opus 5	$0.00618	$0.00618
Sonnet 5	$0.00247	$0.00247
Haiku 4.5	$0.00124	$0.00124

Measured yesterday against content hash dc7c5cb5f911, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gitpin AGENTS.md 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 yesterday.

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.

AGENTS.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - GitPin

Mission

GitPin is an index-free, read-only MCP server for multi-repo evidence pinned to Git HEAD. Answers carry path, line, and full SHA. It has no databases, embeddings, queues, or write tools. GitPin 0.6.3 is the current verified release across npm, the MCP Registry, GitHub Releases, and Pages. It includes the required PR evidence gate, commit-pinned locators, and the legible gate-report failure annotation. Package: gitpin. Tools: pin.*. CLI: gitpin.

Knowledge authority

README.md — entry point: what GitPin is, install, quick start, and publishing.
docs/ — the durable documentation home, indexed by docs/README.md; includes docs/architecture.md, docs/ci.md, docs/cite-spec.md, docs/configuration.md, docs/faq.md, docs/troubleshooting.md, docs/website.md, and the wiki schema template in templates/wiki.yaml.
templates/ — client rules, wiki schema, and gate policy authored for consumers.
src/ — TypeScript sources (see Architecture below); dist/ is the compiled package.
ROADMAP.md, CHANGELOG.md, SECURITY.md, CONTRIBUTING.md, CODE_OF_CONDUCT.md, LICENSE — OSS-standard project files.
docs/current-state.md — current operational state and caveats.
docs/plans/PLANS.md — working plans.

Start here

Read README.md, then docs/current-state.md and docs/architecture.md.
Inspect src/ before changing behavior; dist/ is generated by pnpm build.
Run pnpm install once, then use the canonical commands below.
Preserve existing work: check git status and git log before writing; commit only intended changes to main.

Architecture

src/
  server.ts     Shared pin.* MCP contract and stdio entry
  http.ts       Bearer-authenticated Streamable HTTP transport
  snapshot.ts   Docs/manifests snapshot builder
  registry.ts   repositories.yaml multi-repo Git roots
  git*.ts       HEAD-pinned source operations
  wiki*.ts      Documentation catalog/search/gaps/brief
  cli.ts        init / doctor / brief / verify

Read the full file on GitHub · 121 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.

yesterday First seen · 121 lines · 1,236 tokens per session scan A dc7c5cb5f911

Subscribe to this mod's changes

gitpin AGENTS.md is an instructions file published in the GitHub repository shmindmaster/gitpin (0 stars, last pushed 6d ago), licensed MIT. It adds 1,236 tokens to every session, about $0.0062 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 2026-08-31.

Git and workflow Planning Writing and docs agent-delivery coding-agents devtools evidence mcp

agent-harness-skills AGENTS.md

Instructions for yfge/agent-harness-skills, covering agent harness skills - repository instructions, purpose, rules, validation and commit discipline.

yfge/agent-harness-skills · 450 tokens

agent-harness-skills GEMINI.md

Instructions for yfge/agent-harness-skills: This extension provides reusable skills for repository harness design.

yfge/agent-harness-skills · 111 tokens

loopback AGENTS.md

AGENTS.md instructions for joshidikshant/loopback, covering agent instructions, working the loopback queue, the loop, attachments — reference vs asset and filing feedback (agents report too).

joshidikshant/loopback · 966 tokens

loopback CLAUDE.md

Claude Code instructions for joshidikshant/loopback, a project described as: Interactive feedback layer between the app you're building and your coding agents (MCP). Pins carry the failing request; Claude Code, Codex, and Gemini CLI work one queue; a verified fix turns the pin green.

joshidikshant/loopback · 21 tokens

loopback GEMINI.md

Gemini CLI instructions for joshidikshant/loopback, a project described as: Interactive feedback layer between the app you're building and your coding agents (MCP). Pins carry the failing request; Claude Code, Codex, and Gemini CLI work one queue; a verified fix turns the pin green.