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/modem-dev/hunk/review-skillgit clone --depth 1 https://github.com/modem-dev/hunkWhat 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 | $0.00017 | $0.00342 |
| Opus 5 | $0.00009 | $0.00171 |
| Sonnet 5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
review-skill 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 yesterday.
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
Hunk ships a generated hunk-review skill with every installation. It is the authoritative machine-facing workflow for session selection, efficient review inspection, navigation, reloads, and comments.
Locate the installed skill
hunk skill path
Load or symlink the returned file according to your coding agent's skill mechanism. Resolve the path again after upgrades so the guidance stays aligned with the installed CLI.
For agents that need a stable web-readable URL, use the generated Hunk review skill. The published artifact and installed skill are rendered by the same function; neither is a handwritten copy.
Why it is generated
The checked-in skills/hunk-review/SKILL.md is rendered from typed command metadata and agent error definitions in Hunk's source. Parser help, examples, constraints, and common remedies therefore share ownership instead of drifting as separate handwritten copies.
Do not edit the generated skill directly. Contributors change src/hunk-review/skillDocument.ts, src/session/agent/surface.ts, or src/session/agent/errors.ts, then run:
bun run generate:skill
Use it safely
The skill instructs agents to avoid launching interactive commands such as hunk diff themselves. The user owns the TUI; the agent talks to an already-live review through hunk session *.
For the human workflow around that surface, start with Review with an agent.
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.
- yesterday First seen · 33 lines · 17 tokens per session scan A 713dfc1f5849
review-skill is an agent published in the GitHub repository modem-dev/hunk (8,933 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 342 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
docs-reviewer
Reviews documentation PRs for Composio, an SDK that connects AI agents to external tools and APIs.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
test-doc
Use this agent when the user needs markdown files created in the test-files/ directory. This includes generating test data files, sample documentation, mock content, or any markdown-formatted files for testing purposes.\n\nExamples:\n\n \nContext: User needs sample markdown files for testing a documentation…
node-injection
Hermes CLI 会自动读取本仓库的 CLAUDE.md 文件，包含以下规则：.
retrieval-and-contribution
Agent "retrieval-and-contribution" from Ikalus1988/MisakaNet, covering 检索与贡献指南, 遇到问题时的检索顺序, 步骤详解, lessons 和 reference 的区别 and 贡献新知识.
deep-reflector
Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.