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.
git 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.06090 |
| Opus 5.5 | $0.00014 | $0.02436 |
| Sonnet 5.5 | $0.00007 | $0.01218 |
| Haiku 4.5 | $0.00003 | $0.00609 |
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 6d 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 — 767 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 listed in RELEASING.md Step 3 "Version Update"
- 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 --read-only all- Reads the results of the full run main Claude makes on this clean HEAD
before dispatching this agent (RELEASING.md Step 1b), without re-running
anything. This agent is a sub-agent, so it never starts the full suite
itself; see
CLAUDE/QA.md, "Full QA Is the Coordinator's Gate" - A result recorded for any other tree reads
STALEand fails, so an old green run cannot pass this gate - ABORT if any check fails, is STALE, or has no recorded result: main Claude must run the full gate on this HEAD, fix issues, and re-run release
- Reads the results of the full run main Claude makes on this clean HEAD
before dispatching this agent (RELEASING.md Step 1b), without re-running
anything. This agent is a sub-agent, so it never starts the full suite
itself; see
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.
- 6d ago Changed · -6 lines 8f0992e4f386
- 18d ago Changed · +2 lines 79463870ea81
- 20d ago Changed · +8 lines 685a67042687
- 23d ago Changed 9ffc8bc7923a
- 1mo ago Changed · +6 lines bb4c18cae47e
- 1mo 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 (4 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 6,090 once invoked, about $0.0001 per session on Opus 5.5. 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
release-manager
The Release Manager of the aSPARK team. Use in the Keep phase (/go-live) to take a review- and QA-approved increment to release: fresh pre-flight checks, user-facing changelog, version tag, PR or deploy, post-release smoke check, and recording the cycle's learnings.
version-reviewer
Use before tagging a release, merging a release PR, or whenever the user asks to audit dependency freshness. Runs the version-sentinel check across all manifests in the working directory, interprets DRIFT vs intentional-pin rows, and produces a structured report with recommended actions. Read-only — does not edit…
delivery-lead
Delivery team lead. Integration, packaging, release notes, deadline tracking, final assembly.
change
Changelog and release communication — breaking change documentation, deprecation notices, migration guides.
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…