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 skills/sneg55/agent-starter/adopt-projectnpx skills add sneg55/agent-starter --skill adopt-projectgit clone --depth 1 https://github.com/sneg55/agent-starterWrote 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/sneg55/agent-starter/adopt-project)<a href="https://agentmods.dev/skills/sneg55/agent-starter/adopt-project"><img src="https://agentmods.dev/badge/skills/sneg55/agent-starter/adopt-project.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 | $0.00077 | $0.02157 |
| Opus 5 | $0.00039 | $0.01078 |
| Sonnet 5 | $0.00015 | $0.00431 |
| Haiku 4.5 | $0.00008 | $0.00216 |
Grade A, and why
adopt-project 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 5d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adopt agent-starter in an Existing Project
Use on an existing codebase. Never on a green field - that's /new-project.
An existing project has state to audit, every change is potentially destructive, and adoption must be incremental. So the flow is audit-first, merge-don't-overwrite, opt-in per component.
Safety rails (read first)
- Create a branch before any write:
git checkout -b adopt/agent-starter. Everything below is reversible by dropping the branch. - Read every file before modifying it. Append and merge; never replace a file the developer wrote.
- After each merge-tier step, run the project's own test suite (and linter, if present). A red suite means stop and surface it.
- If the project has no tests, say so explicitly and default to the non-invasive tier only.
- Surface contradictions between starter patterns and existing conventions; never resolve them silently.
Phase 1: Interview
Ask one at a time:
- Components - which are you interested in? (hooks / skills / CLAUDE.md + memory / lint configs / code patterns / "audit first, then decide")
- Repo path - local path to agent-starter, e.g.
~/code/agent-starter(only needed if files will be copied).
Phase 2: Audit (read-only)
Build a gap report before proposing anything.
Detect the stack:
package.json+tsconfig.json→ TypeScript/JavaScriptpyproject.toml/setup.py/requirements.txt→ Python- Both → monorepo: audit each half separately
- Neither → other stack; only Tier 1 and CLAUDE.md apply
Inventory (present as a table: component | what exists | starter offering | conflicts):
- Lint/format: ESLint configs (flat or legacy),
biome.json, Prettier; ruff (ruff.tomlor[tool.ruff]in pyproject), mypy/pyright configs - Instructions:
CLAUDE.md,CLAUDE.local.md,.claude/rules/,AGENTS.md - Hooks:
.claude/settings.jsonhook entries; agent-starter hooks already installed system-wide (~/.claude/hooks/.agent-starter-version- record the stamped version to compare against the repoVERSION) - Skills: which starter skills are already present system-wide - check
~/.claude/skills/{commit,commit-push-pr,simplify,remember,dream,new-project,adopt-project,reflect}. Hooks and skills are user-global, so anything already installed already covers this project - don't re-propose it. - Tests:
package.jsonscripts.test, pytest/tox config, Makefile targets - File-size health: run
bash <repo-path>/hooks/check-codebase-health.shfrom the project root, orfind src -name '*.ts' -o -name '*.py' | xargs wc -l | sort -rn | head -20 - Patterns already present: central error registry? env boundary? Result
types? (grep for scattered
process.env/os.environ, rawthrow new Error/raise Exception)
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.
- 5d ago First seen · 186 lines · 77 tokens per session scan A f0294e114c3e
adopt-project is a skill published in the GitHub repository sneg55/agent-starter (77 stars, last pushed 3d ago), licensed MIT. It adds 77 tokens to every session and 2,157 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
economist-style
Apply The Economist style guide to written content. Use when editing markdown, HTML, documentation, or any written text that needs professional editing for clarity, precision, and brevity. Detects weasel words, fillers, passive voice, and style issues.
branch-recap
Takes stock of what a branch actually changed, before it gets pushed — works out the scope itself, then lays the change out group by group in one pass: files touched, what was done and why, how, and what deserves a second look, quoting code only where a remark needs it rather than reprinting the diffs. Closes on a…
audit-context
Measures where a project's Claude context is going before applying any of clean-context's levers. Reports what Glob discovers with and without ignore files applied, the twenty largest files in the repo and which are generated, the cumulative size of every CLAUDE.md loaded for this working directory, and how many MCP…
slack-changelog
Turns what changed in a release into a Slack changelog a non-technical audience can read: filtered to what they would actually notice, one bullet per idea, plain language, no code vocabulary. Works out the scope itself across however many repositories sit in the working directory (a project can span several…
ignore-setup
Set up a project so Claude stops discovering lockfiles, generated code, minified assets and binaries on every search — a managed .ignore, the Glob setting that makes Glob obey it, and a short read-deny list for secrets. Use when someone asks for a .claudeignore, asks to exclude files from the context, says Claude…
plugin-commands
Commands for validating, testing, iterating on, and releasing plugins in this marketplace (claude-toolbelt) — plugin validate, watcher-parity check, eval, --plugin-dir dev loop, plugin tag. Use when validating a plugin before pushing, running skill evals, developing a plugin without touching the installed cache, or…