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-with-an-agentgit 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 | $0.00020 | $0.00588 |
| Opus 5 | $0.00010 | $0.00294 |
| Sonnet 5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
review-with-an-agent 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Hunk window stays with you. Your agent uses non-interactive hunk session commands from another terminal to inspect the same review, navigate it, and leave inline notes.
Start the review
hunk diff
Keep that window open. Normal Hunk sessions register with a local loopback daemon so the session CLI can find them.
Give the agent the skill
In the agent's shell, locate the skill bundled with the installed Hunk version:
hunk skill path
Ask the agent to load that file and use it for the review. A portable prompt is:
Load the Hunk skill and use it for this review. Run `hunk skill path` to get the skill path.
The skill tells agents not to launch the interactive TUI themselves. It teaches them to use the session surface instead.
What the agent does
A typical agent flow is:
hunk session list
hunk session get --repo .
hunk session review --repo . --json
hunk session navigate --repo . --file src/App.tsx --hunk 2
hunk session comment add --repo . --file src/App.tsx --new-line 42 --summary "Check this boundary"
review --json exposes structure without forcing the full patch into agent context. The agent should request --include-patch only when it actually needs raw unified diff text.
Agent notes remain spatially attached to the code they explain. Use { and } to move between annotated hunks while keeping the full changeset visible.
Give the agent the docs
These docs are published as plain Markdown so an agent can read them without scraping HTML:
- /llms.txt — index of every page, for pulling only what is needed.
- /llms-small.txt — compact corpus for tight context budgets.
- /llms-full.txt — the complete docs in one file, around 130KB.
Any docs page URL also returns its Markdown source with .md appended, so https://hunk.dev/docs/reference/cli.md is the CLI reference as the agent should read it.
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.
- 3d ago First seen · 63 lines · 20 tokens per session scan A 2d72d0408249
review-with-an-agent is an agent published in the GitHub repository modem-dev/hunk (8,933 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 588 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
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
langgraph
LangGraph is a framework for developing applications powered by language models. Integrating LangGraph with the Model Context Protocol (MCP) allows agents to utilize tools defined across one or more MCP servers, enabling seamless interaction with external data sources and services.
verify-agent
구현 완료 후 fresh-context 검증 전용. typecheck → lint → build → test 파이프라인 독립 실행. 단순 에러(import·타입) 자동 수정, 비수정 가능 에러 분류 보고. Use proactively — 비단순 코드 변경 완료 직후 사람 호출("검증해줘"·"빌드 확인")을 기다리지 말고 자율 spawn한다. 완료 주장 전 필수(verification.md 자율 검증 §11). 사람 발화에 의존하지 않는다. /handoff-verify 스킬에서도 자동 스폰. 구현 자체는 tdd-guide나 impl-worker 사용.
database-engineer
PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.
accessibility-expert
WCAG 2.2 AAA accessibility specialist.