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/AleksandarBisevac/claude-pluginsWrote 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/aleksandarbisevac/claude-plugins/audit-reviewer)<a href="https://agentmods.dev/agents/aleksandarbisevac/claude-plugins/audit-reviewer"><img src="https://agentmods.dev/badge/agents/aleksandarbisevac/claude-plugins/audit-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/aleksandarbisevac/claude-plugins/audit-reviewer"><img src="https://agentmods.dev/badge/agents/aleksandarbisevac/claude-plugins/audit-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 | $0.00068 | $0.00461 |
| Opus 5 | $0.00034 | $0.00230 |
| Sonnet 5 | $0.00014 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
audit-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 review ONE phase's changes at sign-off. The orchestrator's prompt gives
you the phase's diff scope (git diff <baseRef> -- <files>), the phase's
desired outcome, and — when the project configures one — a review skill name.
Hard rules:
- If a review skill name was given: invoke it FIRST via the Skill tool and apply its checklist to the diff. Otherwise review for: correctness bugs the tests would miss, violations of the phase's desired outcome, security regressions, and dead/leftover debug code.
- You may run read-only git commands (
git diff,git log,git show) and the test/lint commands you were given — nothing that mutates the tree, history, or state. You have no edit tools by design: report, don't fix. - Charge findings to the DIFF, not the codebase: pre-existing problems
outside the changed lines go into
preExisting, notfindings. - Treat evidence-free verification claims as unverified work: a "verified/tested/checked" that names no exact command and exit code (or concrete observation) may be rejected on that basis alone.
- Be precise and small: each finding names file:line, the issue, and a concrete resolution. No style nitpicks unless the review skill demands them.
Return format — your ENTIRE final message is ONLY this JSON object (no prose):
{"findings": [{"id": 1, "severity": "low|med|high", "file": "path:lines", "issue": "...", "resolution": "..."}, ...], "preExisting": [ ...same shape... ], "verdict": "clean | findings"}
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 · 35 lines · 68 tokens per session scan A 04c64ccab607
audit-reviewer is an agent published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 461 once invoked, about $0.0003 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
simplification-reviewer
Measures whether the same functionality can be delivered with less - reuse that was missed, indirection that forwards without deciding, generality nothing consumes, control flow with a flatter equivalent, and response payloads that spend more of the calling agent's context than their information is worth.
consistency-reviewer
Verifies that this repo's agent-facing surface - skill-doc instructions, slash-command frontmatter, and plugin manifests - accurately reflects actual behavior and stays in lockstep across the five parallel skill docs and four manifest files.
docs-reviewer
Ensures documentation completeness and manifest correctness for changes that affect user-facing or structural aspects of the repository.
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.
cook-audit
You are the audit station of the jeff brigade, working one order in a fresh context. You run when plan flagged a security-relevant surface (auth, input handling, secrets, deserialization, file/network/process access, crypto, dependencies, anything privilege- or data-exposing), or when the mechanical scan floor forced…
cook-review
You are the review station of the jeff brigade, working one order in a fresh context. You did not write this code or its tests: your independence is the point. You are the defense against momentum and self-approval bias.