Chalk Labs
Need help deploying 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.
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/sh-ai-x-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.
About
Use cases: devops
Reviews
Write a reviewNo 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. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/bootstrap
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
ReadWriteGlobBashAskUserQuestion
What's inside
- Skill name
bootstrap- Description
- 0-arg setup for CLAUDE.md, AGENTS.md, hooks, and optional CI.
- License
- MIT
- Allowed tools
- Read, Write, Glob, Bash, AskUserQuestion
- Instructions
- 76 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves any shell command
Files (1)
- SKILL.md
SKILL.md (first lines)
> [← Skills index](../../README.md) · Detailed reference: [skills/bootstrap/SKILL.md](../../skills/bootstrap/SKILL.md) # `/dev-kit:bootstrap` Run the deterministic setup pipeline, then offer the optional installers. The unconditional output is the minimal project context: `CLAUDE.md`, `AGENTS.md`, `.dev-kit/.active-hooks.json`, and the linked SSOT indexes. Do not create noise files or ask recurring SessionStart questions. ## Contract 1. Run sanity, codebase-map, hook-matrix, and `lib/write_project_md.py`. 2. On the first run only, ask the guard policy question below. 3. Ask `Also install CI templates (ci-setup)? [y/N]`; N is the default. 4. If Y, call `lib/ci_setup.py:install_ci_config()`; the result matches the legacy `/dev-kit:bootstrap-full` end state. If N, print the unavailable features list and suggest `/dev-kit:ci-setup --force` later. 5. Ask `Also configure operator-global git defaults (rebase.autoStash + pull.rebase)? [Y/n]`; Y is the default unless `--skip-git-defaults` is supplied. 6. Resolve `$DEV_KIT_TEAM` through `hooks/lib/team-resolve.sh`; only the explicit team-on path may strip `.dev-kit` from `.gitignore`. Every deterministic stage is read-only except its documented output. Preserve existing JSON keys and use the linked docs/code as the implementation SSOT. ## Guard policy (one-time bootstrap choice) Guards default off everywhere: main, worktrees, detached checkouts, and user scope. User-scope plugin installation never enables repository guards. Only when neither `.claude/settings.json` nor `.claude/settings.local.json` already contains `env.DEV_KIT_GUARDS`, ask: ```text Enable repository guards (worktree, git, TDD)? [y/N] If yes, save to project scope or this checkout only? [project/local] ``` `N` leaves the effective value off. `Y + project` writes `DEV_KIT_GUARDS=on` to `.claude/settings.json`; `Y + local` writes it to `.claude/settings.local.json`. Preserve all existing JSON keys. Later On later bootstrap runs, report the current value and do not ask again. **SessionStart never asks this question**; a main-branch-specific prompt is intentionally deferred. Resolution is shell > local > project > default off. User scope is ignored for this key. The policy controls `worktree`, `git`, and `TDD` guards only; other safety and verification hooks keep their own contracts. ## Flags and outputs Hidden flags: `--target DIR`, `--skip-sanity`, `--skip-map`, `--slim|--full`, `--strict`, `--persist-audit`, `--skip-ci`, `--skip-git-defaults`, `--yes`, `--force`, `--skip-verify`. `--yes` accepts CI and git defaults; it does not change guard policy. `--skip-ci` is equivalent to answering `n`. Without CI, `/dev-kit:ci-doctor`, `/dev-kit:bump`, the 15 workflow templates, the pre-push hook, and `/dev-kit:evaluate`'s CI harness are unavailable until `/dev-kit:ci-setup --force` runs. With CI, installation is idempotent unless `--force` is supplied; `--skip-verify` skips only CI Phase 3 verification. ### y branch (when chosen) `install_ci_config()` installs the CI workflows and marker; this is the non-default path and preserves legacy `/dev-kit:bootstrap-full` parity. ### n branch (default) The unavailable-features list is printed; add CI later with `/dev-kit:ci-setup --force`. The final hand-off is `/dev-kit:build <first-feature>` (or `/dev-kit:plan` for an idea that needs a PRD). For the full stage audit, template list, git-default details, and output matrix, read [`skills/bootstrap/SKILL.md`](../../skills/bootstrap/SKILL.md).
From sh-ai-x/dev-harness-kit, MIT.
More from sh-ai-x/dev-harness-kit
- 0.587score
harness-effectiveness
sh-ai-x
0-arg harness-effectiveness report.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
gate-select
sh-ai-x
Unified 3-dimension picker for project / session / AI-judge gates.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
babysit-pr-local
sh-ai-x
0-arg local-mode PR babysitter.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
harness-mode
sh-ai-x
Session-scoped local-hook mode picker — fast (all optional local hooks off), full (default, all on), or custom (interactive per-local-hook picker via…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
guard-mode
sh-ai-x
Session-scoped on/off toggle for the tdd-guard, worktree-guard, and git-guard hard-block hooks.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
babysit-pr
sh-ai-x
0-arg restart-safe PR check, diagnose, fix, and hand-off loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
build
sh-ai-x
0-arg.
SkillAFreshness: A★ 1Claude Code - 0.552score
codex-cache-update
sh-ai-x
Refresh the dev-kit Codex marketplace checkout and synchronize the versioned plugin cache.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
bump
sh-ai-x
Explicit version bump of `.claude-plugin/plugin.json` + push of `chore/bump-vX.Y.Z`.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
evaluate
sh-ai-x
0-arg eval extension.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
evidence-plan
sh-ai-x
Idea → cited research → HTML proposal (human confirms) → /dev-kit:plan hand-off.
SkillBFreshness: B★ 1Claude Code - 0.544score
ci-update
sh-ai-x
Detect + selectively apply drift between installed CI templates and current dev-kit source.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 2
- Open issues
- 8
- Last commit (this folder)
- Sep 28, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sh-ai-x/dev-harness-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sh-ai-x
- 0.587score
harness-effectiveness
sh-ai-x
0-arg harness-effectiveness report.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
gate-select
sh-ai-x
Unified 3-dimension picker for project / session / AI-judge gates.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
babysit-pr-local
sh-ai-x
0-arg local-mode PR babysitter.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
harness-mode
sh-ai-x
Session-scoped local-hook mode picker — fast (all optional local hooks off), full (default, all on), or custom (interactive per-local-hook picker via…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
guard-mode
sh-ai-x
Session-scoped on/off toggle for the tdd-guard, worktree-guard, and git-guard hard-block hooks.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
babysit-pr
sh-ai-x
0-arg restart-safe PR check, diagnose, fix, and hand-off loop.
SkillAFreshness: A★ 1Claude Code +9
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 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.
Cite this page
bootstrap skill. Agent Mart. https://agentmart.dev/skills/sh-ai-x-bootstrap (last updated 2026-10-24)