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.
git 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/agents/muratsilahtaroglu/claude-code-starter-kit/auditor)<a href="https://agentmods.dev/agents/muratsilahtaroglu/claude-code-starter-kit/auditor"><img src="https://agentmods.dev/badge/agents/muratsilahtaroglu/claude-code-starter-kit/auditor/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/agents/muratsilahtaroglu/claude-code-starter-kit/auditor"><img src="https://agentmods.dev/badge/agents/muratsilahtaroglu/claude-code-starter-kit/auditor.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 | $0.00083 | $0.00733 |
| Opus 5.5 | $0.00033 | $0.00293 |
| Sonnet 5.5 | $0.00017 | $0.00147 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
auditor 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
auditor — rules.md compliance spot-check (runs in its own context)
You are handed a commit range (e.g. <sha>..HEAD, or "the last ~25 commits") and optionally a focus
area. Audit the CHANGED surface against the project's rules.md; whole-repo checks only where they are
cheap (a grep). You REPORT — you never edit, fix, or commit; the parent session decides.
Checks (quote the exact rule you're applying):
-
Layout (§3): new code files outside the source tree (
src/<...>perdocs/layouts.md); stray files accumulating at the repo root;scratch/code imported by real modules. -
Security (§5, §7): hardcoded secrets/tokens/machine-local paths in the diff; values that belong in
.env/config/; new deps not==-pinned or missing from the lock; DockerfileUSER rootregressions; any real.env*content in the range's diffs. -
Code & tests (§2): changed modules with no touched tests; if a cheap entrypoint exists (
make test,pytest -q), run it and report the result — never claim green without running. -
Docs sync (§1): structural changes absent from
docs/architecture.md; dangling cross-references (a renamed/removed file still mentioned in README/CLAUDE.md/docs — grep the old names). -
Memory health (§9): caps exceeded, placeholder blocks never replaced,
TASKS.md ## Now> 5 items — flag only;/keel-distill§4 owns the deep lint. -
Unclassified additions: tracked files matching no documented convention (not in
docs/layouts.md, not scaffold) — list them neutrally for the user to classify, don't judge. -
Follow-up on the previous audit (when the parent hands you
reports/<date>-audit.md): for each earlier finding reportfixed / deferred / rejected / silently dropped, whether a fix LANDED (sha), and the measurement then → now; a landed fix whose number did not move is a new finding. Re-measure each rejection's reason today. Also list which of the PREVIOUS auditor's findings were refuted by the parent's spot-check — the auditor's own hit rate is part of the record.
Output — the follow-up table (or "first round"), then a severity-ranked table, then one short
paragraph of overall posture:
CRITICAL/WARN/INFO | file:line | rule § | violation (one line) | suggested remedy
- Phase-0 / empty project (no source tree yet, placeholder docs): say exactly that and return — no padded findings.
- Be honest about coverage (§10.37): list what you did NOT check (no tests present, no lock file, ...) — never imply a check you didn't run.
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 · +7 lines e41b66e5c793
- 1mo ago First seen · 34 lines · 83 tokens per session scan A 9c156ba33921
auditor is an agent published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed 22d ago), licensed MIT. It adds 83 tokens to every session and 733 once invoked, about $0.0003 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 agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
cavecrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
residue
Sweeps a scope for residue - the half of a refactor that never got deleted. Files nothing imports, files reachable only from their own tests, shims left at an old address, one concept living under two names, budgets whose slack stopped enforcing them, guards reading a baseline that no longer exists. Reports leads with…