agent-context-and-stml

Support for adding review explanations to code changes through a sidecar JSON file, with optional rich terminal markup called STML.

In plain words
What is it for?
Use it to attach summaries and notes to diffs or patches, arrange files for review, and render terminal notes when STML is enabled.
Why use it?
It keeps the reasoning behind changes available during review and provides plain-text fallback when rich markup is unsupported.

Agent

Install

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.

agentmods
npx agentmods add agents/modem-dev/hunk/agent-context-and-stml
Clone the repo
git clone --depth 1 https://github.com/modem-dev/hunk
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 311 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00311
Opus 5 $0.00008 $0.00156
Sonnet 5 $0.00003 $0.00062
Haiku 4.5 $0.00002 $0.00031

Measured 2d ago against content hash 7d523481403b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-context-and-stml 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.

website/src/content/docs/docs/agents/agent-context-and-stml.md · 38 lines

What it actually says

Live session comments are the recommended workflow. A sidecar is useful when the annotations already exist before Hunk starts or need to travel with a patch.

Load a JSON sidecar

hunk diff --agent-context notes.json
hunk patch change.patch --agent-context notes.json

The sidecar can set narrative file order and attach hunk-level annotations. Keep it concise: one changeset summary, short file summaries, and only rationale that improves the review. The visible UI prioritizes hunk notes rather than generic explainer cards.

A compact example lives at examples/3-agent-review-demo/agent-context.json in the repository.

Opt into STML

STML is experimental rich markup for terminal note bodies. It is off by default:

hunk --experimental diff --agent-context notes.json

The launch flag is the authority for that session; a reload cannot turn the capability on later. Plain summary text remains required as the fallback.

Before sending markup, an agent should inspect support and width:

hunk session context --repo . --json
hunk markup guide
hunk markup render - --width <reported-noteMarkupWidth>

Only send --markup when experimentalFeatures includes stml. Keep colors symbolic and markup compact so notes retain a clear spatial relationship to their code.

Changes

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.

  1. 2d ago First seen · 38 lines · 16 tokens per session scan A 7d523481403b

Subscribe to this mod's changes

agent-context-and-stml is an agent published in the GitHub repository modem-dev/hunk (8,933 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 311 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.

Related

Other agents, from other repositories

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

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.

VoltAgent/voltagent · 0 tokens

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.

IBM/mcp-context-forge · 0 tokens

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.

sangrokjung/claude-forge · 134 tokens

database-engineer

PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.

yonatangross/orchestkit · 28 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens