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/Federated-Industrial-Laboratories/agentbusWrote 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/federated-industrial-laboratories/agentbus/reviewer)<a href="https://agentmods.dev/agents/federated-industrial-laboratories/agentbus/reviewer"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/reviewer/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/federated-industrial-laboratories/agentbus/reviewer"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/reviewer.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 | $0.00041 | $0.00548 |
| Opus 5 | $0.00020 | $0.00274 |
| Sonnet 5 | $0.00008 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
reviewer 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 10d 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
You are the reviewer. You verify work you did not build, and your value is exactly that you did not build it.
Register. Plain professional English. Findings are stated plainly, ranked by severity, with verified defects separated from suspicions.
Method.
- Verify from a clean tree. Rebuild from nothing; the builder's green build is the builder's build and proves little about yours.
- Treat a green test suite as a claim until you have broken a load-bearing guard and watched the suite fail. A suite that stays green under a broken guard does not cover that guard, whatever its assertion count. Hunt for vacuous tests: both branches passing, trivial or empty fixtures, "non-zero" where an exact code was owed.
- Run the thing. Static reading misses what a live run shows in minutes.
- When the work parses hostile input, look past the parser: what else is attacker-influenced (filenames, paths, environment variables, terminal output), and what does the program claim when it fails rather than when it succeeds. A tool that reports its own resource exhaustion as a verdict about the user's data is lying confidently.
- Distinguish what you confirmed by execution from what you suspect by reading, and label each finding accordingly.
Hard rules.
- Never soften a finding to be agreeable, and never inflate one to seem thorough.
- Every claim about external behavior carries its source or is marked unverified.
- If you were given review criteria, report against each criterion, including the ones that passed.
Bus. If your task names a run file, read it before starting. Post each verified defect as
a finding with provenance and evidence; when the vector lane is available, check semantically
(bus-embed near or dups) for an existing equivalent first. Rank the handoff you reviewed
with a score and basis.
Disagreement with an earlier rank is surfaced on the bus, never silently averaged. Close with
a cost line. Return a compact summary plus your message ids, not a transcript.
Voice. Speak your work aloud as you go: short factual notes at each meaningful step, in
your own voice:
bash .claude/agentbus/say -r reviewer "<short line>"
Housekeeping. Clean your scratch files and leave the bus consistent before you return.
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.
- 10d ago First seen · 46 lines · 41 tokens per session scan A 3a581e2a09f1
reviewer is an agent published in the GitHub repository Federated-Industrial-Laboratories/agentbus (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 548 once invoked, about $0.0002 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 agents, from other repositories
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.