agentmods.dev

h2 CLAUDE.md

Project instructions for developing and releasing the h2 software, including isolated tests and a required quality-check command. They also describe how to choose version changes and prepare a production release.

In plain words
What is it for?
Use them when writing tests, checking code before a commit, changing the software version, updating the changelog, or preparing a release.
Why use it?
They keep tests from changing the developer’s real configuration files and make sure releases include the required checks, version updates, documentation, and build steps.

Instructions file

159 7d ago A scan 305 tokens copy · 100% MIT
View the source file dcosson/h2
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 instructions/dcosson/h2/claude-md
Clone the repo
git clone --depth 1 https://github.com/dcosson/h2
Per session 305 This file is loaded in full into every session.
When invoked 305 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00305 $0.00305
Opus 5 $0.00152 $0.00152
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured 3d ago against content hash b66f628862b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

h2 CLAUDE.md 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.

Origin

This is a copy

100% identical to h2 AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 29 lines

What it actually says

Testing Rules

Never use config.ConfigDir() in tests. Tests must not touch the real h2 config directory. Use setupFakeHome(t) or a similar pattern that sets H2_DIR to a temp directory and calls config.ResetResolveCache(). This prevents test side effects on the real ~/.h2 directory and ensures test isolation.

Release Process

Commit Quality Gate

Before every feature commit, run make check and ensure it passes.

When doing a production release, follow this sequence:

  1. Ensure you are on the main branch first.
  2. Fetch and fast-forward main to origin/main (git fetch origin main && git pull --ff-only origin main).
  3. Determine the version bump and update the h2 version:
    • If unsure what bump to use, ask the user.
    • Use semver rules:
      • patch for non-breaking changes.
      • for pre-1.0 versions: minor for breaking changes.
      • for 1.0+ versions: major for breaking changes.
  4. Update docs/CHANGELOG.md with changes since the last version tag and its tagged commit.
  5. Run all test suites and ensure they pass.
  6. Run make check and ensure it passes.
  7. Run make build-release and ensure it passes.
  8. Tag the current HEAD with the release version.
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. 3d ago First seen · 29 lines · 305 tokens per session scan A b66f628862b2

Subscribe to this mod's changes

h2 CLAUDE.md is an instructions file published in the GitHub repository dcosson/h2 (159 stars, last pushed 7d ago), licensed MIT. It adds 305 tokens to every session, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to h2 AGENTS.md, differing in 0 lines, and is treated as a copy.

CommitsGit and workflowReleasesTesting
Related

Other instructions, from other repositories

planning-with-files AGENTS.md

AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.

OthmanAdi/planning-with-files · 2,236 tokens

modelrelay AGENTS.md

Instructions for ellipticmarketing/modelrelay, covering agent instructions, post-feature testing, git commits, release process (mandatory) and test architecture.

ellipticmarketing/modelrelay · 1,514 tokens

heptabase-cli-skills AGENTS.md

Instructions for heptameta/heptabase-cli-skills, covering heptabase-cli-skills, layout, before you commit and releases.

heptameta/heptabase-cli-skills · 276 tokens

mcp-wordpress-remote AGENTS.md

Instructions for Automattic/mcp-wordpress-remote, covering mcp-wordpress-remote, commits, pre-publish release gate, version and testing.

Automattic/mcp-wordpress-remote · 543 tokens

stiletto CLAUDE.md

Instructions for benjamin-bader/stiletto, covering stiletto — contributor & agent guide, commit messages: conventional commits (required), breaking changes, examples and how releases work.

benjamin-bader/stiletto · 977 tokens

git-authoring AGENTS.md

Instructions for n-shadloo/git-authoring, covering git authoring conventions, usage modes, ground rules, workflow and 1. gather context.

n-shadloo/git-authoring · 10,785 tokens