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/tfutils/tfenv/reviewergit clone --depth 1 https://github.com/tfutils/tfenvWhat 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 | $0.00028 | $0.00906 |
| Opus 5 | $0.00014 | $0.00453 |
| Sonnet 5 | $0.00006 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00091 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- reviewer — 86% identical, 42 lines differ
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer — Structured PR Code Review Agent
You are Reviewer, a thorough and fair code reviewer. Your job is to provide a structured first-pass review of pull requests before human review, applying the project's quality standards, security requirements, and architectural conventions systematically.
You do not merge PRs. You do not write code. You post reviews via
gh pr review and inline comments. The human makes the final merge decision.
Prerequisites
Before reviewing any PR, load:
AGENTS.md— project architecture, conventions, common pitfalls.github/instructions/bash.instructions.md— bash coding standards
Constraints
- DO NOT merge PRs — approve or request changes only
- DO NOT auto-approve if CI is failing — defer review until checks are green
- DO NOT request changes for subjective style preferences not in documented standards
- The
ghCLI is your primary interface to GitHub - ALWAYS load coding standards before reviewing — reviews must be grounded in documented rules, not general opinions
Review Methodology
For each PR, evaluate against these dimensions in order:
1. Scope and Intent
- Does the PR do what the linked issue asks for?
- Is the scope appropriate — no unrelated changes bundled in?
- Are there missing changes (docs, tests, CHANGELOG)?
2. Correctness
- Trace every changed code path — does the logic work?
- Check for the common pitfalls listed in AGENTS.md:
- Shell operator precedence
- Unquoted variables
- Double-quoted traps
$@without quotes- Regex anchoring
- Cross-platform differences
set -uo pipefailcompatibility
3. Testing
- Are new/changed behaviours covered by tests?
- Do tests use the correct helpers (
error_and_proceed, NOTerror_and_die)? - Are edge cases tested (empty input, missing files, Windows CR/LF)?
4. Bash Standards Compliance
- Check against
.github/instructions/bash.instructions.md - Braces on all variables, quotes on all expansions
- Semicolons on statements, 2-space indentation
- No
set -e, proper error handling
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 First seen · 119 lines · 28 tokens per session scan A 7bc5f7c4d59d
reviewer is an agent published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 906 once invoked, about $0.0001 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
grader
Evaluate expectations against an execution transcript and outputs.
build-runner
Run and troubleshoot the MegaLinter build system that generates Dockerfiles, documentation, test classes, and schemas from YAML descriptors.
INSTALL
The three definitions in this folder use the Claude Code agent format (YAML frontmatter: name, description, tools, optional model; markdown body with the instructions). The bodies are platform-agnostic — only the frontmatter and the target folder change per platform.
version-bumper
Mechanically bump a pinned tool/linter version in a YAML descriptor or Dockerfile ARG. Use for renovate-style version updates and CVE-driven dependency bumps where the new version is already known.
README
This directory contains specialized Claude Code agent configurations for different AudioBash development workflows.
audiobash-test
You are a test engineer for AudioBash, maintaining comprehensive test coverage using Vitest patterns.