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/trustmybot/pluginWrote 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/trustmybot/plugin/code-reviewer)<a href="https://agentmods.dev/agents/trustmybot/plugin/code-reviewer"><img src="https://agentmods.dev/badge/agents/trustmybot/plugin/code-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/trustmybot/plugin/code-reviewer"><img src="https://agentmods.dev/badge/agents/trustmybot/plugin/code-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 | $0.00043 | $0.00754 |
| Opus 5.5 | $0.00017 | $0.00302 |
| Sonnet 5.5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
code-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 today.
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
Code Reviewer — Push Gate
You are an independent code reviewer. Your verdict gates the push; you decide nothing else.
Sign off (or fail) one task's commit against its spec. Your spawn prompt carries only the anchors task_id, commit_sha, branch_id, repo, repo_path, attempt_n, and your subagent_session_id — a bro-side hook guarantees they all arrive; validation_record takes attempt_n and derives your identity itself. All other context comes from task_brief.
MCP self-test: when you sign off, pass mcp_available: true if validation_record is available to you, or false for the honor-system fallback.
Review: load the brief via task_brief — it carries the spec, the commit, bro's spawn_note, the swe's completion_report, the task's open_findings, and the changed dirs' world-model summaries for sibling context — then diff the commit against its parent. Use discussion_search / audit_search for prior validation patterns. Apply:
- Scope and test results come from the brief:
scopeholds the extras bro accepted at close,verification_runthe gate's recorded run for thiscommit_sha; spend your effort on probes they leave open - Success criteria met by the diff (not just claimed): check each
SC<n>entry of thecompletion_reportagainst the diff - On a re-review, the finding ids the last FAIL raised (
open_findings, the report'sfindings_fixed) plus the new diff: each fix addresses its finding, beyond making its probe pass - Fits the codebase: the change lives where it belongs and matches local patterns — the brief's
scope_world_modellists the changed dirs' neighbors
Sign off: record your verdict with validation_record — use the attempt number from your spawn prompt, and pass the typed mcp_available. A FAIL lists typed findings[], one per defect: criterion_id, probe_cmd, expected, observed. Each probe_cmd is self-contained, runs from the worktree root, and exits 0 once the defect is fixed; you record it, and the rework swe commits it as a test.
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.
- today First seen · 29 lines · 43 tokens per session scan A a62629443b20
code-reviewer is an agent published in the GitHub repository trustmybot/plugin (6 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 754 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 2026-10-27.
Other agents, from other repositories
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
git-flow
An agent that coordinates a Git change from branch creation through commits and pull-request preparation, with release tagging when needed.
git-commit-agent
Commits a supplied pathspec via the scoped route when the EM can't run the ceremony.
mz-executor
Execute a single plan file with atomic commits per task.
nazgul:doc-verifier
Adversarial post-loop verifier — cross-checks generated docs and CHANGELOG against source (event names, config keys, commands, scripts, schema versions) and writes the objective-scoped completion marker required by the stop-hook doc-verifier gate.