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 agentmods add instructions/metagit-ai/metagit-cli/agents-mdgit clone --depth 1 https://github.com/metagit-ai/metagit-cliWrote 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/instructions/metagit-ai/metagit-cli/agents-md)<a href="https://agentmods.dev/instructions/metagit-ai/metagit-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/metagit-ai/metagit-cli/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01937 | $0.01937 |
| Opus 5 | $0.00968 | $0.00968 |
| Sonnet 5 | $0.00387 | $0.00387 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
agents 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 4d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metagit
What This Is
Metagit gives you situational awareness across Git repositories. It helps multi-repo projects feel manageable, discoverable, and cohesive. It captures cross-repository relationships and project knowledge in easy to understand version controlled manifests.
Day-1 Agent OS loop: docs/agents-quickstart.md — install → context pack → aos next → compile/ACL → complete.
After Every Task
After meaningful work, run GROW:
- Prepare: Run
task qa:prepushand resolve any errors. Rerun until all failures are resolved. - Ground: what changed in reality?
- Record: update
.mex/ROUTER.mdand relevant.mex/context/files - Orient: create or update a
.mex/patterns/runbook if this can recur - Write: bump
last_updatedon changed scaffold files and runmex logwhen rationale matters
Navigation
At the start of every session, read .mex/ROUTER.md before doing anything else.
For full project context, patterns, and task guidance — everything is there.
Metagit — agent quick reference
For agents instructed to use Metagit (not necessarily to contribute to this repository).
Install: uv tool install metagit-cli · set METAGIT_AGENT_MODE=true · PyPI name metagit-cli.
Quickstart: docs/agents-quickstart.md · example examples/agent-aos-loop/
Session start (from repo with .metagit.yml):
metagit context pack --tier 2 --json
metagit prompt workspace --kind session-start --text-only
Skills: metagit skills install --scope user · MCP: metagit mcp install --scope user
| Need | Command |
|---|---|
| Workspace map / repo cards | metagit context pack --tier 0|1|2 --json |
| Find managed repo | metagit search "…" --json |
| Repo CI topology | metagit project repo ci show / detect / set (--json) |
| Search repo file contents | metagit workspace grep "…" --json |
| Grep backend (ripgrep) | metagit workspace grep info --json |
| Catalog | metagit workspace list --json |
| Operational prompts | metagit prompt list |
| Scoped repo text | metagit context repomix --profile bugfix-local --project P --repo R |
| Latest release / notes | metagit version check --json |
| Self-update | metagit version upgrade --apply --json |
| Agent profile / apply | metagit agent profile show / metagit agent apply --vendor cursor |
| Campaigns | metagit campaign list · metagit campaign new · metagit campaign expand |
| Derived surgical project | metagit project derived create -n N --from P/R · refresh · include · exclude |
| Skills surface | metagit skills surface --json |
| ACL isolate agent checkout | metagit branch allocate · metagit lease acquire --allocate · metagit worktree create |
| ACL file claims | metagit claim declare · metagit claim check |
| Task graph / intent | metagit task create · metagit task expand · metagit task ready · metagit task complete |
| Context compile | metagit context compile --project P --repo R [--task-id N] --json |
| Context switch | metagit context switch <project> [<repo>] · --json · MCP metagit_context_switch |
| Nav (human) | metagit nav / navigate [-p PROJECT] [--repo REPO] |
| Semantic ownership | metagit semantic declare · metagit semantic owners · metagit semantic conflicts |
| Merge orchestration | metagit merge enqueue · metagit merge integrate · metagit merge status |
| Agent scheduler | metagit schedule next · metagit schedule status · metagit schedule policy show |
| Agent OS (composition) | metagit aos status · metagit aos doctor · metagit aos next (coord alias) |
| Local Atlas | metagit atlas init · metagit atlas generate · metagit atlas validate · metagit atlas query |
| Agent coordination skill | metagit skills show metagit-agent-coordination |
| Agent OS skill | metagit skills show metagit-aos |
| Agent coordination (ACL) | docs/reference/agent-coordination.md |
| Task graph (RFC-0008) | docs/reference/task-graph.md |
| Context compiler (RFC-0009) | docs/reference/context-compiler.md |
| Semantic ownership (RFC-0010) | docs/reference/semantic-ownership.md |
| Merge orchestrator (RFC-0011) | docs/reference/merge-orchestrator.md |
| Agent scheduler (RFC-0012) | docs/reference/agent-scheduler.md |
| Agent OS (RFC-0013) | docs/reference/aos.md |
| Metagit Atlas (RFC-0014) | docs/reference/atlas.md |
| Feature registry (all modalities) | docs/reference/modality-feature-registry.md |
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.
- 4d ago First seen · 119 lines · 1,937 tokens per session scan A a84039e8f464
agents is an instructions file published in the GitHub repository metagit-ai/metagit-cli (2 stars, last pushed 6d ago), licensed MIT. It adds 1,937 tokens to every session, about $0.0097 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.
Other instructions, from other repositories
logic CLAUDE.md
Instructions for lemur47/logic, covering claude.md, project overview, commands, install dependencies and run api server (hot reload).
mcp-redmine-rest CLAUDE.md
Claude Code instructions for alsimoes/mcp-redmine-rest, covering claude.md, what this is, layout (src-layout), tool registration pattern and deliberately missing tools.
fizzy-do-mcp AGENTS.md
Instructions for ryanyogan/fizzy-do-mcp, covering using vite+, the unified toolchain for the web, vite+ workflow, start, develop and execute.
asana-project-ops CLAUDE.md
Instructions for n0zer0d4y/asana-project-ops, covering claude.md, build and development commands, build the project (uses esbuild), run in development mode with ts-node (requires node.js 18+) and start the built server.
claudebench CLAUDE.md
Instructions for fblgit/claudebench, covering claude.md, project overview, critical commands, codebase architecture and handler-centric design.
mcp-better-vibe-kanban CLAUDE.md
Claude Code instructions for yigitkonur/mcp-better-vibe-kanban, covering claude.md, what this is, build & run, http transport (default port 3000) and environment variables.