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-updategit 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-update)<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-update"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-update/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-update"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-update.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 | $0.00068 | $0.02152 |
| Opus 5.5 | $0.00027 | $0.00861 |
| Sonnet 5.5 | $0.00014 | $0.00430 |
| Haiku 4.5 | $0.00007 | $0.00215 |
Grade C, and why
keel-update scanned grade C 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 1mo 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 deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/keel-latest # idempotent — clear the stale clone a previous /keel-update run left behind How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/keel-update — sync this project with the latest Keel template
Use when the kit was cloned a while ago and the template has since improved (hardened hooks, doc
fixes, workflow updates). Pull model: run it IN the project, review diffs, approve. Non-destructive is
the hard rule (same spirit as /keel-adopt): nothing is applied without a shown diff + an explicit yes.
One channel: the kit is clone-only (the plugin/marketplace half was retired in v0.8.23 — it
delivered only the tooling, double-fired hooks alongside a clone, and needed marketplace access that
locked-down networks block). Everything therefore syncs HERE, through the buckets below. If a project
still has keel@keel installed from before, removing it is the fix for double-firing hooks.
1. Fetch the latest template (never inside the project)
rm -rf /tmp/keel-latest # idempotent — clear the stale clone a previous /keel-update run left behind
git clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kit /tmp/keel-latest
git -C /tmp/keel-latest rev-parse --short HEAD # record for the handover line
2. Classify every template path into three buckets
- PROTECTED — never touched (project-owned):
HANDOVER.md·LESSONS.md·TASKS.md·PLAN.md·docs/handover-archive.md·docs/lessons-retired.md·docs/architecture.md·docs/adr/*(except the kit-owned0000template and the folderREADME.md— those are TOOLING) ·CLAUDE.md·README.md·LICENSE·config/·requirements/*.{txt,lock}contents ·.env.examplevalues ·src/·tests/(except the kit-ownedtests/unit/test_keel_*.pymatrix — that is TOOLING, same carve-out as the ADR0000template; never put project tests in atest_keel_*.pyfile) ·scratch/·research/findings ·reports/·.claude/last-audit·.claude/project-owner·.claude/keel-caps·.claude/lessons-backlog·.claude/tasks-backlog(project state: audit clock + governance owner + tuned caps + entry-budget baseline) ·.claude/agents/team-*.md(project agent-team charters, owner-authored — the kit ships none;.claude/agent-team-sessionsis git-ignored and never syncs). - REVIEW — likely tailored; full diff, apply hunk-by-hunk with approval:
rules.md·.claude/settings.json(permissions merge = union, keep the project's) ·.gitignore·.pre-commit-config.yaml·pyproject.toml·Makefile·Dockerfile*·.dockerignore·docker-compose.yml·.editorconfig·.github/*(workflows + PR template) ·docs/layouts.md·docs/user_manual.md· folder READMEs that carry KIT DOCTRINE inside a PROTECTED tree —scratch/README.md,tests/README.md,tests/*/README.md: the folder's CONTENTS are the project's, but the README states the kit's rule for that folder and projects tailor it, so it is diffed hunk-by-hunk rather than skipped with the tree (without this the scratch-as-evidence rule of v0.8.25 could never reach an adopted project) ·reports/team/README.md(the index TEMPLATE inside the PROTECTEDreports/tree: its header is kit doctrine — status vocabulary, index scope — while its lines are the project's; diff the header, never the lines). - TOOLING — template-owned; summarize changes, one approval for the batch:
.claude/skills/**·.claude/hooks/**·.claude/*.py·.claude/claude-launch-wrapper.sh(kit-owned tools that sit at the.claude/root — team-addresses, ritual-report, the launch wrapper) ·.claude/agents/{researcher,verifier,auditor,observer,README}.md·.claude/rules/README.md(+ example) ·tests/unit/test_keel_*.py·docs/security.md·docs/steering.md·docs/memory-files.md·.claude/keel-caps.example(the key reference; the project's own.claude/keel-capsstays PROTECTED) ·docs/adr/0000-adr-template.md·docs/adr/README.md·docs/assets/·CONTRIBUTING.md(kit-meta by its own first line) · folderREADME.mds.
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.
- 1mo ago Changed · +4 lines 2e4c3715d443
- 1mo ago Changed 6a2e9ff057c7
- 1mo ago Changed bd8edb51a1bf
- 1mo ago Changed 9a954b05cded
- 2mo ago First seen · 98 lines · 68 tokens per session scan C 0305d2f61f0c
keel-update is a skill published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 2,152 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C 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.