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 muratsilahtaroglu/claude-code-starter-kit --skill keel-adoptgit clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kitWrote 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/muratsilahtaroglu/claude-code-starter-kit/keel-adopt)<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-adopt"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-adopt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-adopt"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-adopt.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.00704 |
| Opus 5.5 | $0.00017 | $0.00282 |
| Sonnet 5.5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade B, and why
keel-adopt 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 2mo 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Safe bulk-add of only-missing files (never `cp -r` over the top; never `rm -rf .git`): Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/keel-adopt — bring an existing project under Keel discipline (brownfield)
Use when the project already has code + history (rules.md §0, Mode B). Goal: overlay the template's discipline without clobbering anything. Non-destructive is the hard rule — propose the full plan, get approval, then act. Nothing is overwritten without a shown diff + an explicit yes.
1. Inventory & classify
Bucket every template path against the repo and report the three lists before touching anything:
- missing → safe to add as-is.
- present (project already has its own:
README.md,.gitignore,pyproject.toml,Makefile,CLAUDE.md,Dockerfile, ...) → merge, never replace. - conflicting (same path, different intent) → show a diff, ask.
Safe bulk-add of only-missing files (never cp -r over the top; never rm -rf .git):
rsync -av --ignore-existing <keel>/ ./ --exclude .git
2. Back-fill the living docs from real code
docs/architecture.md← reverse-engineer the current module map (what each real dir/file does; status ✅).HANDOVER.md← write the FIRST session block: (a) what already exists / works today (not blank placeholders); seedLESSONS.mdwith known gotchas andTASKS.md ## Nowwith the actual next work.- Capture the adoption itself as an ADR in
docs/adr/(what was added / merged / deferred and why).
3. Reconcile discipline
- Merge, don't replace an existing
CLAUDE.mdand.claude/settings.json(union the permissions; keep the project's). - Map the existing source layout to the nearest
docs/layouts.mdprofile — don't create parallel folders beside it. - Prune template parts the project won't use, cascading reference cleanup (rules.md §0a).
- Multi-user team? Ask who the project OWNER (founder) is — default the adopter, never assumed —
and write their
git config user.nameinto.claude/project-owner: governance files become owner-only via theowner-guardhook (docs/steering.md "Multi-user"). Single-user: skip, no file.
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.
- 2mo ago First seen · 45 lines · 42 tokens per session scan B 639e2ae5ead9
keel-adopt is a skill published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 704 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
docs-governance
Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks for documentation governance, project-knowledge organization, documentation integrity, or a deterministic docs audit…
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
coordinator
Take over as coordinator of the current LangWatch drive: read the live state from disk (the lane roster, the newest handover, the shape counters), report it, then work the handover's next action by writing manifests and spawning lanes. Replaces pasting a brief out of a handover document - the state is read, never…
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.
company-mirror
Run a PenguinHarness organization that mirrors a real company — one digital twin per real colleague, each twin's desk bound to that colleague's chat bot, twins answering what the handbook already knows and relaying the rest to one another instead of hiring, scheduling and filing tickets.