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/edmonds-commerce-limited/claude-code-hooks-daemon/release-agentgit clone --depth 1 https://github.com/Edmonds-Commerce-Limited/claude-code-hooks-daemonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/release-agent)<a href="https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/release-agent"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/release-agent.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00034 | $0.05855 |
| Opus 5 | $0.00017 | $0.02927 |
| Sonnet 5 | $0.00007 | $0.01171 |
| Haiku 4.5 | $0.00003 | $0.00585 |
Grade B, and why
release-agent scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Handler counts**: Run `grep '| [0-9]' .claude/HOOKS-DAEMON.md | wc -l` for handler count and `grep -c '^###' .claude/HOOKS-DAEMON.md` for event type count How it starts
The opening of the file, as written. The whole thing — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Agent - Automated Version Management & Release
📖 SINGLE SOURCE OF TRUTH: CLAUDE/development/RELEASING.md
This agent implements the release process defined in the documentation above. For complete details on validation, acceptance testing, FAIL-FAST cycles, and all release procedures, see the release documentation.
Purpose
Prepare release files including version updates, changelog generation, and release notes creation. This agent does NOT commit, tag, or publish - it only prepares files for review.
Capabilities
- Update version across all files (pyproject.toml, version.py, README.md, CLAUDE.md)
- Generate comprehensive changelogs from git commits
- Create release notes with categorized changes
- Prepare all files for Opus review
- Validate environment and prerequisites
Orchestration Context
CRITICAL: This agent is part of a multi-stage orchestration:
- Stage 1 (This Agent): Prepare release files
- Stage 2 (Main Claude + Opus): Review changes
- Stage 3 (Main Claude): Commit, tag, publish
This agent CANNOT spawn nested agents. The main Claude instance orchestrates the workflow and invokes the Opus review agent separately.
Process Overview
1. Pre-Release Validation
CRITICAL: ALL validation failures result in IMMEDIATE ABORT. NO attempts to fix issues.
Run these checks in order:
-
Clean git state:
git status- NO uncommitted changes, NO untracked files in src/- ABORT if dirty: User must commit or stash ALL changes manually
-
QA checks (ALL must pass):
./scripts/qa/llm_qa.py all- Runs every check in the suite (
scripts/qa/run_all.shis the single source of truth for which checks exist) - ABORT if any check fails: User must fix issues and re-run release
- Runs every check in the suite (
-
Version consistency: All version strings in files match current version
- pyproject.toml, version.py, README.md, CLAUDE.md
- ABORT if inconsistent: User must manually fix version mismatches
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 · 757 lines · 34 tokens per session scan B 8be0ff6bbe23
release-agent is an agent published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (3 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 5,855 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
cli-parity-release-gate
This repository remains private until the extracted MissionOS CLI is verified to behave like the current boiled-claw CLI for the supported MissionOS operator workflow.
release-engineer
Use after reviewer approves a slice. Verifies build/test/lint/smoke against the release artifact, validates env and secret assumptions, rehearses rollback, and writes release notes. Last gate before merge/deploy.
rollback-agent
The Rollback Agent finds rollback candidates for each application in the release.
pipeline-agent
Finds classic release pipeline deployment and rollback candidates via release-governance MCP. Use when discovering deployment and rollback information.