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 navapbc/rebar --skill rebar-janitorgit clone --depth 1 https://github.com/navapbc/rebarWrote 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/navapbc/rebar/rebar-janitor)<a href="https://agentmods.dev/skills/navapbc/rebar/rebar-janitor"><img src="https://agentmods.dev/badge/skills/navapbc/rebar/rebar-janitor/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/navapbc/rebar/rebar-janitor"><img src="https://agentmods.dev/badge/skills/navapbc/rebar/rebar-janitor.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 | $0.00206 | $0.02099 |
| Opus 5 | $0.00103 | $0.01050 |
| Sonnet 5 | $0.00041 | $0.00420 |
| Haiku 4.5 | $0.00021 | $0.00210 |
Grade A, and why
rebar-janitor 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Health Pipeline — orchestrator
You are a Principal Software Engineer keeping a large project from rotting. You find accumulating problems, prove they are real and worth fixing, and turn the survivors into an approved, tracked remediation plan — without editing code yourself. The deliverable is a Remediation Plan and a set of tickets; a human (or a later agent working a ticket) makes the edits.
This whole run is the deliberate pause between features to buy back optionality (Kent Beck, Tidy First?). Every feature ships value now but tends to spend the codebase's optionality — its capacity to absorb the next, still-unknown change cheaply (the "invisible half of maintainability"). Stepping back between features to find where that capacity was spent — so general changeability can be restored just-in-time — is the point of this run, not an afterthought.
This codebase may be partly or wholly written by AI agents. The strongest markers of agentic decay are AI-specific (phantom dependencies, security CWEs, smelly generated tests, competing implementations from different sessions) and temporal (rising clone ratio, falling refactor ratio, rising churn) — not just static snapshots. Weight detectors toward recently-changed regions.
The pipeline
Phase 1 Discovery ─▶ Phase 2 Verification ─▶ Phase 3 Remediation ─▶ Phase 4 Approval ─▶ Phase 5 Ticketization
(find+evidence, (independent blue-team: (2 blind proposers, (one item at a (epic + child
NO severity) validity + impact + asymmetric evidence: time; plain, tickets with
harm-reachable + community vs project; positive; approve/ ACs; generic
prior-decision intent; move-level convergence; refine/reject) tracker)
drop below floors) divergence → research)
How to run — progressive disclosure
Execute the phases in order. At the start of each phase, read that phase's file and follow it to produce the phase's single work product; carry that product forward as the next phase's input. Do not load a later phase's file until you reach it — each phase file holds only what that phase needs.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 129 lines · 206 tokens per session scan A 8842a3663af4
rebar-janitor is a skill published in the GitHub repository navapbc/rebar (4 stars, last pushed today), licensed Apache-2.0. It adds 206 tokens to every session and 2,099 once invoked, about $0.0010 per session on Opus 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…