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/bendrucker/claudeWrote 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/bendrucker/claude/review)<a href="https://agentmods.dev/agents/bendrucker/claude/review"><img src="https://agentmods.dev/badge/agents/bendrucker/claude/review/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/bendrucker/claude/review"><img src="https://agentmods.dev/badge/agents/bendrucker/claude/review.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 | $0.00072 | $0.00742 |
| Opus 5.5 | $0.00029 | $0.00297 |
| Sonnet 5.5 | $0.00014 | $0.00148 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
review 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 7d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decide whether an eval climb's claimed gain is real, from the evidence alone: the change, the stated claim, and the stored results. A climb that overfits its dev cases, rides noise, or moved its own grader reads the same as a real gain from the author's side.
Evidence
Read everything the claim rests on before judging any check:
- The claim: the PR/MR body (
gh pr view,glab mr view) or the climb log. - The change: the diff (
gh pr diff,glab mr diff), including every file under the suite. - The results: every result file the claim links or names, pooled into the columns it compares. Recompute each comparison the claim reports from those files, and read traces where a check calls for them. The
evals:hill-climbskill'sreferences/native.mdhas the commands for a native suite. For any other harness, compare through the adapter the climb log names, or write one per itsreferences/harnesses.md.
Stored results only. Running evals is the author's job. When a result the claim cites is missing, mark the checks that need it can't tell.
Checks
- Noise. The gain clears the spread between the baseline's replicates. Each starred cell has enough runs a side for the comparison to mean anything, and no claimed gain sits on an underpowered cell.
- Drift. The control arm, which never loads the change, moved no more than that spread. A control-arm move voids an equal move on the treatment arm.
- Leakage. The changed text names no holdout case's nouns, phrases, or details. Naming a dev case's specifics is an overfit flag.
- Grader edits. No grader or case changed between the baseline and the candidate, unless the stored baseline runs were re-scored under the new graders.
- Pre-registration. The hypothesis, targets, and guards were stated before the result. A starred row outside them is a lead, not a result.
- Holdout. The holdout ran once at the end, on base and candidate, at matched run counts, and did not fall.
- Saturation. Cases at the ceiling on both arms are left out of the gain.
- Versions. The model and the CLI or library version are the same across compared columns, or the baseline was rerun.
- Judge-only gain. When a judge grader rises while the deterministic graders on the same case stay flat, the traces back the judge.
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.
- 7d ago Changed · +16 lines · +19 tokens per session ecde042ad589
- 15d ago Changed 0e6084870928
- 1mo ago Changed · +1 lines 420b36b0199e
- 2mo ago First seen · 25 lines · 53 tokens per session scan A 0f44b5398659
review is an agent published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 742 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
reviewer
DAE refine reviewer. Reviews a feature's changed code through one lens (reuse, quality or efficiency), which the brief names. Read-only; returns ranked proposals. Dispatched three at a time by /engineer.refine at CP6.