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 hariharapanigrahy/layerkit --skill layerkit-checker-assistgit clone --depth 1 https://github.com/hariharapanigrahy/layerkitWrote 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/hariharapanigrahy/layerkit/layerkit-checker-assist)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-checker-assist"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-checker-assist/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/hariharapanigrahy/layerkit/layerkit-checker-assist"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-checker-assist.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 | $0.00025 | $0.00399 |
| Opus 5.5 | $0.00010 | $0.00160 |
| Sonnet 5.5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
layerkit-checker-assist 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 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.
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.
What it actually says
layerkit-checker-assist
Assist a human checker. This skill is read-only on the approval path.
Allowed
- Read proposals, maps,
{projectDir}/memory/, doctor output, eval results. - Produce a risk checklist markdown:
- sources quality (primary docs vs blog vs catalog-only)
- invented or uncited rules
- privacy gaps / missing consent
- empty maps treated as complete
- maker ≠ checker identity
- client package verification coverage of primary intents
- Suggest residual questions for the human reviewer.
- Point at failing gates (
npm run eval:ci) without re-running network research unless asked.
layerkit proposal list
layerkit doctor
layerkit memory list --type proposals
# optional local: npm run eval:ci
Forbidden (hard)
- Calling
layerkit proposal apply,approve,promote, or any approve/promote CLI - Writing
checks[]on a proposal or mutating proposal/map JSON in place - Self-approving as the same actor as the maker
- Inventing missing evidence to make a proposal look ready
- Submitting proposals as maker while acting as checker in the same session (strict)
Output
Checklist only. Human checker decides approve/reject via:
layerkit proposal approve <id> --by <humanId> --role checker
# or
layerkit proposal reject <id> --by <humanId> --role checker --comment "..."
Success criteria
- Checklist covers sources, invention risk, privacy, maker≠checker
- No apply/approve side effects from this skill
- Residual questions are actionable
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 First seen · 53 lines · 25 tokens per session scan A dc8daec0b536
layerkit-checker-assist is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 399 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
code-reviewer
Code review automation for TypeScript, JavaScript, Python, Go, Swift, and Kotlin. Analyzes PRs for complexity, risk, SOLID violations, and code smells. Use when reviewing PRs, analyzing code quality, or generating review checklists.
pr-review-expert
Systematic PR review with blast-radius analysis, security scanning, and breaking-change and test-coverage deltas. Use when reviewing PRs that touch shared libraries, APIs, database schemas, auth, or security-sensitive code.
api-design-reviewer
Review REST API designs for quality, consistency, and breaking changes. Lints OpenAPI specs, generates scorecards, and detects breaking changes between versions. Use when designing APIs, reviewing contracts, or managing API versioning.
qa-review
Validate that implemented code fully satisfies Story acceptance criteria, respects rules, and introduces no regressions. This is the hard quality gate — no pass means no delivery. Activate after implementation is complete.
consistency-check
Detect inconsistencies across related artefacts and governance constraints. Activate after story generation, after plan preparation, before implementation, or after remediation attempts. Reports issues — does not fix them.
chinese-code-review
Chinese-language guidance for giving professional, tactful code-review feedback while still calling out real problems.