Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rajbos/ai-engineering-fluency/main/.claude/agents/repo-health-scan.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/repo-health-scan)<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/repo-health-scan"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/repo-health-scan/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/rajbos/ai-engineering-fluency/repo-health-scan"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/repo-health-scan.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 | $0.00055 | $0.02494 |
| Opus 5.5 | $0.00022 | $0.00998 |
| Sonnet 5.5 | $0.00011 | $0.00499 |
| Haiku 4.5 | $0.00006 | $0.00249 |
Grade A, and why
repo-health-scan 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 yesterday.
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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Health Scan
One run = one finding → one issue → one PR. The finding comes from
scripts/repo-health-scan.js, a deterministic scanner (no AI cost) that covers
eight topics:
| Topic | Source |
|---|---|
| Style & validation | ESLint (vscode-extension/eslint.config.mjs) non-complexity rules |
| Naming consistency | ESLint naming-convention + file names that break their tree's dominant convention |
| Cyclomatic complexity | ESLint complexity, sonarjs/cognitive-complexity, max-depth, max-lines-per-function |
| Large files | Non-blank line count ≥ 1500 (≥ 3000 for tests) |
| Dead code | Unused variables/imports, unreachable code, exports nothing references |
| Duplicate code | scripts/check-code-duplication.js clone groups (≥ 14 lines) |
| Modularization | Layer-boundary imports, runtime import cycles, CLI re-declaring a shared src/ function |
| Technical debt | TODO/FIXME/HACK markers, @ts-ignore/@ts-nocheck suppressions |
Every finding has a stable id (rh-<12 hex>). The issue body carries it in a
visible repo-health-id: rh-… footer; any id that appears in any repo-health
issue — open, fixed, or closed as not planned — is never picked again. That is
how the daily run avoids duplicate issues and respects a human's "won't fix".
Pick your mode
- You were given an issue (e.g. the Copilot coding agent was assigned a
repo-healthissue, or the prompt names an issue number): read itsrepo-health-idand location, then start at Step 4. - Otherwise: start at Step 1 and choose the finding yourself.
Step 1 — Install and check capacity
cd vscode-extension && pnpm install --frozen-lockfile && cd ..
gh label create repo-health --color 0e8a16 --description "Daily repo-health scan finding" 2>/dev/null || true
open_prs=$(gh pr list --label repo-health --state open --json number --jq length)
[ "$open_prs" -lt 3 ] || { echo "STOP: $open_prs repo-health PRs already open"; exit 1; }
If that exits non-zero (3 or more repo-health PRs open), stop and report that —
unreviewed PRs are piling up, and adding another only adds merge conflicts.
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.
- yesterday First seen · 190 lines · 55 tokens per session scan A 748b06236cf9
repo-health-scan is an agent published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,494 once invoked, about $0.0002 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 2026-10-26.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.