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 skills add hams-ollo/zen-agent-skills --skill project-bootstrapgit clone --depth 1 https://github.com/hams-ollo/zen-agent-skillsWrote 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/skills/hams-ollo/zen-agent-skills/project-bootstrap)<a href="https://agentmods.dev/skills/hams-ollo/zen-agent-skills/project-bootstrap"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/project-bootstrap.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 5.1 | $0.00148 | $0.02165 |
| Opus 5 | $0.00074 | $0.01082 |
| Sonnet 5 | $0.00030 | $0.00433 |
| Haiku 4.5 | $0.00015 | $0.00216 |
Grade A, and why
project-bootstrap 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 3d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
project-bootstrap
The umbrella "fire up my harness" skill. Turn a new or bare repository into a real project with a sane baseline, then bring up work tracking. It does not reimplement tracking; it calls init-worktracking for that. Think of it as the front door and init-worktracking as the room behind it.
What it lays down
A minimal, widely-agreed baseline, matched to the detected stack. Never a heavy opinionated framework:
.gitignorefor the detected language(s), plus OS/editor cruft..editorconfigfor consistent whitespace across editors.- Linter/formatter config: for Python,
ruff(lint + format); for JS/TS,prettier+eslint. Emitted from the house code-style layer, only the config, not an install. LICENSE: ask which; default MIT with the user's name/handle.README.mdstub: project name, one-line purpose, setup and test placeholders.- Then it calls
init-worktrackingto addAGENTS.md,.tasks/, and (by tier)ROADMAP.md/CHANGELOG.md.
Design choices
These decisions are settled (resolved with the author); these four are not up for re-litigation:
- First-class stacks are Python and JavaScript/TypeScript. Everything else gets a generic baseline plus a clearly marked
<!-- TODO -->. Add stacks as real need appears, not speculatively. - Configs, not installs. The skill writes config files; it does not run
npm install,uv add, orpre-commit install. It offers those commands for the user to run. - pre-commit is opt-in, not default, so small repos are not burdened.
- Linter/formatter configs come from the house code-style layer in
templates/, not bare tool defaults. They are opinionated but documented, adjustable at three levels (confirm-time, per-repo, kit-wide), and never overwrite a config the repo already has. See House code-style layer.
House code-style layer
The linter/formatter defaults live in templates/ as a swappable house
layer, the code-conventions parallel to the kit's prose module
.agents/rules/house-style.md. Full detail and rationale are
in templates/house-code-style.md; the essentials:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 114 lines · 148 tokens per session scan A 3a603a5f76f9
project-bootstrap is a skill published in the GitHub repository hams-ollo/zen-agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 148 tokens to every session and 2,165 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
rig-epic
Plan and run a multi-ticket epic: decompose a feature into parent + child items and stack PRs on a shared integration branch instead of landing each on main. Use when children interleave (one item's runtime contract depends on another's incomplete state) — stacking keeps each child PR reviewable without temporarily…
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-workspace
Manage GSD workspaces — create, list, or remove isolated workspace environments.
gsd-inbox
Triage and review open GitHub issues and PRs against project templates and contribution guidelines.
gsd-pause-work
Create context handoff when pausing work mid-phase.
gh
Install and configure the GitHub CLI (gh) for AI agent environments where gh may not be pre-installed and git remotes use local proxies instead of github.com. Provides auto-install script with SHA256 verification and GITHUBTOKEN auth with anonymous fallback. Use when gh command not found, shutil.which("gh") returns…