A project setup tool that activates development safety rules for a coding-agent project. It adds instructions to CLAUDE.md and installs a Git push guard, a check that helps control pushes to remote repositories.

Use it after setting up the core hermit to activate the development rules, install the strict push-guard profile, and configure companion plug-ins.

It gives the project shared safety guidance and protects Git pushes from being handled too casually. It also checks whether the core setup is already present.

hatch — Skill by gtapps

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 skills/gtapps/claude-code-hermit/hatch

Any agent

npx skills add gtapps/claude-code-hermit --skill hatch

Clone the repo

git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code, Codex.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,033 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00065	$0.05033
Opus 5	$0.00032	$0.02516
Sonnet 5	$0.00013	$0.01007
Haiku 4.5	$0.00006	$0.00503

Measured today against content hash c603f09d13c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

hatch scanned grade B with 1 finding 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 today.

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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

- Capability scan: `ls .claude/skills/ 2>/dev/null` — list skill directory names. Match if any of the following dir names are present: `commit`, `create-pr`, `pr`, `pull-request`, `release`, `git-commit`. Record the matc

plugins/claude-code-dev-hermit/skills/hatch/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Activate Dev Hermit

Set up the language-agnostic safety layer for this project. Requires claude-code-hermit core to be initialized first.

The plugin's identity in v0.3.0+: a thin wrapper around (a) git-push-guard strict-profile hook, (b) a CLAUDE-APPEND template (safety or standard) injected into the project's CLAUDE.md, (c) dev workflow skills (/dev-pr, /dev-quality, /dev-test) available but only prescribed in standard mode. There is no built-in implementer agent — operators use the native Agent tool, or custom subagents, all governed by the injected rules.

Plan

1. Check prerequisites

Check if .claude-code-hermit/config.json exists in the current project.

Missing: print this block and stop:

## ▶ Next step — type this now

    /claude-code-hermit:hatch

I can't run setup wizards for you (they're operator-run by design).
After it finishes, come back and type `/claude-code-dev-hermit:hatch`.

Present: run .claude-code-hermit/bin/hermit-run domain-hatch preflight claude-code-dev-hermit and parse the JSON verdict. Branch on action:
- upgrade-core-package / upgrade-core-applied → relay the remedy string verbatim to the operator and stop.
- verify → this version (self_version) is already stamped; continue through the wizard, Step 3's block sync is the idempotency guard.
- full → continue through the wizard.
- ok: false → relay message and stop.

2. Capability scan + choose mode

Run all detection in a single parallel turn:

Bash:

Existing PR template: ls .github/PULL_REQUEST_TEMPLATE.md .gitlab/merge_request_templates/Default.md .bitbucket/pull_request_template.md docs/pull_request_template.md 2>/dev/null | head -1.
Installed plugins: claude plugin list 2>/dev/null or read .claude/settings.json.
Remote forge (for commands.pr_create): git remote get-url origin 2>/dev/null — classify by substring:
- github.com or github. → FORGE=github, DEFAULT_PR_CREATE="gh pr create"
- gitlab.com or gitlab. → FORGE=gitlab, DEFAULT_PR_CREATE="glab mr create"
- bitbucket.org → FORGE=bitbucket, DEFAULT_PR_CREATE="" (no universal CLI — operator must supply)
- anything else or no remote → FORGE=custom, DEFAULT_PR_CREATE=""
Capability scan: ls .claude/skills/ 2>/dev/null — list skill directory names. Match if any of the following dir names are present: commit, create-pr, pr, pull-request, release, git-commit. Record the matched names.
Base-branch detection: git branch -r --format='%(refname:short)' 2>/dev/null | sed 's|^origin/||' — collect remote branch names. Record which of the following are present: main, master, develop, development, dev, trunk. Call this set CANDIDATE_BASES.

Read the full file on GitHub · 316 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.

today Changed · +5 lines c603f09d13c9
2d ago First seen · 311 lines · 65 tokens per session scan B fe1405b70d7c

Subscribe to this mod's changes

hatch is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 5,033 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Git and workflow Security ai ai-agent anthropic claude claude-code claude-code-plugin

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

hatch