Skip to content
Agentmart
Submit a tool

metagit-bootstrap

Create or refine a local .metagit.yml.

Skill by metagit-ai

IndexedMIT★ 4
Write a review

Chalk Labs

Need help deploying metagit-bootstrap?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/metagit-ai-metagit-bootstrap

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Create or refine a local .metagit.yml. Default is deterministic `metagit init`; do not dump detect payloads into context.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/metagit-bootstrap

What's inside

Skill name
metagit-bootstrap
Description
Create or refine a local .metagit.yml. Default is deterministic `metagit init`; do not dump detect payloads into context.
License
MIT
Metadata
internal: true
Instructions
60 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • bootstrap-config.sh · scripts/

SKILL.md (first lines)

# Metagit bootstrap

Create a valid `.metagit.yml` with **minimal tokens**. Prefer code over sampling.

## Token rules

- Default to **deterministic init**. Do not start with MCP sampling or `config example`.
- Never run `metagit detect repo_map` (full directory maps blow the context window).
- Never paste full detect YAML/JSON into the conversation. Write it to a file and read only the fields you need.
- Prefer `detect … -o summary` on stdout. Use `--output-file` for the full payload.

## Default path (deterministic)

```bash
export METAGIT_AGENT_MODE=true
# missing manifest:
metagit init --kind application --no-prompt
# or:
SKILL_ROOT="$(python3 -c "import metagit, pathlib; print(pathlib.Path(metagit.__file__).parent / 'data/skills/metagit-bootstrap')")"
"$SKILL_ROOT/scripts/bootstrap-config.sh" .
metagit config validate -c .metagit.yml
```

`bootstrap-config.sh` writes a minimal application scaffold when `.metagit.yml` is missing and prints `status=written|exists`. Do not overwrite a valid manifest without explicit confirmation.

Existing manifest: `metagit config validate -c .metagit.yml`. Patch with `metagit config patch` — do not regenerate from detect dumps.

`metagit init` writes one file. Split an existing umbrella with `metagit config split --by all --dir .metagit.d` when concurrent edits collide on `.metagit.yml`. After a split, edit the fragment, not the root.

## Optional enrichment (file-backed)

Only after init, and only if catalog fields are still empty:

```bash
mkdir -p .metagit/.detect
metagit detect repository -p . -o summary
metagit detect repository -p . -o json --output-file .metagit/.detect/repository.json
# jq '.language, .kind, .frameworks' .metagit/.detect/repository.json
```

Stdout of `--output-file` is a compact line (`status=written path=… bytes=… format=json`). Do not `cat` the file unless selecting fields.

`detect repo` / `detect project` follow the same rule: `--output-file .metagit/.detect/…` or `-o summary`. Skip them if summary already has language/kind.

## Incremental patch

```bash
metagit config show -c .metagit.yml --json
metagit config patch -c .metagit.yml --op set --path <path> --value <json> --save
metagit prompt repo -p P -n R -k repo-enrich --text-only
```

## MCP sampling (optional, not default)

Use `metagit_bootstrap_config` only when the host supports `sampling/createMessage` **and** the operator asked for a richer draft than `init`. Discovery context is already a short artifact list — do not attach repo maps. Validate YAML; write `.metagit.yml` only with `confirm_write=true`. Plan-only: return the prompt, do not invent repos.

## Safety

- Never overwrite `.metagit.yml` silently.
- Never emit secrets. Prefer placeholders for tokens.
- Do not invent repositories or unverifiable dependencies.

From metagit-ai/metagit-cli, MIT.

Signals

Stars
4
Forks
0
Open issues
0
Last commit (this folder)
Sep 16, 2026 (1 month ago)
Last release
Oct 2, 2026 (29 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from metagit-ai

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get metagit-bootstrap running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying metagit-bootstrap?

CallGet help
Cite this page

metagit-bootstrap skill. Agent Mart. https://agentmart.dev/skills/metagit-ai-metagit-bootstrap (last updated 2026-10-24)