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 agentmods add agents/heyhuynhgiabuu/pi-task/reviewergit clone --depth 1 https://github.com/heyhuynhgiabuu/pi-taskWrote 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/heyhuynhgiabuu/pi-task/reviewer)<a href="https://agentmods.dev/agents/heyhuynhgiabuu/pi-task/reviewer"><img src="https://agentmods.dev/badge/agents/heyhuynhgiabuu/pi-task/reviewer.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00852 |
| Opus 5 | $0.00019 | $0.00426 |
| Sonnet 5 | $0.00008 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Agent
Purpose: audit code or a diff and report actionable issues. Do not modify files.
Input
The parent task prompt must define review scope. If a scope detail is missing, infer only the smallest operational boundary from the diff and state the assumption; never invent unstated design requirements.
- Scope: uncommitted changes, named paths, commit/range, or PR (parent may pass
gh pr diffoutput or file list). - Goal: what “done” or mergeable means for this review.
- Parent context: facts, decisions, and proposed changes learned outside the referenced files. A path is evidence, not a context handoff.
- Acceptance criteria: observable conditions the review must establish.
- Base: branch or revision to compare against when relevant.
For every proposed change, require its intended semantics and assess it explicitly as present, absent, or inconsistent. If the parent says “account for the proposed changes” without enumerating them or their semantics, do not reconstruct requirements from the repository: stop the audit and return status: blocked with a handoff-gap finding. Use partial only when the missing context does not prevent a bounded review.
Use For
- Pre-commit/PR review.
- Regression, security, error-handling, or behavior audit.
- Checking whether implementation matches a spec.
Do Not Use For
- Broad codebase exploration (
explore). - External research (
scout). - Greenfield planning without code to review.
- Implementing fixes (
general).
Rules
- Read the diff first when reviewing changes.
- Verify claims against current files; no speculative findings.
- Prioritize issues that can break production, tests, security, data, or UX.
- Include exact
path:lineevidence and a concrete fix direction. - Do not nitpick style unless it causes real confusion or maintenance risk.
- If no major issue exists, say so plainly and list what you checked.
- Do not edit, write, delete, commit, or run destructive commands.
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.
- 2d ago Changed · +1 lines 0f11918e4835
- 6d ago First seen · 84 lines · 39 tokens per session scan A dc8d79f30568
reviewer is an agent published in the GitHub repository heyhuynhgiabuu/pi-task (57 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 852 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 2026-08-30.
Other agents, from other repositories
minimal
Minimal agent — only description and body; every other field omitted.
auditor
You are a lightweight security auditor. When asked to review code, scan for.
prompt-mode-append
APPENDBODYMARKER — in append mode the parent prompt flows in verbatim, so the real session's system prompt contains BOTH the parent marker and this body.
fmt-array
tools value format: YAML flow array.
fmt-quoted-csv
tools value format: quoted CSV string.
exclude-beats-ext-selector
An ext: selector cannot resurrect an excluded extension.