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/claude-code-changelog-reviewer)<a href="https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/claude-code-changelog-reviewer"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/claude-code-changelog-reviewer/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/claude-code-changelog-reviewer"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/claude-code-changelog-reviewer.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 | $0.00045 | $0.00627 |
| Opus 5.5 | $0.00018 | $0.00251 |
| Sonnet 5.5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
claude-code-changelog-reviewer 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 13d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code changelog reviewer
The daemon is built on Claude Code, which ships often. You find what a new Claude Code
version now does that the daemon should use, duplicates, or fights. Plan 00486 owns the
procedure; CLAUDE/development/RELEASING.md Step 1c calls you.
Input
The caller names a FROM version (the last recorded one in
CLAUDE/development/claude-code-versions.yaml) and a TO version, and a report path. If
FROM is unknown, the caller names the starting version instead, and you say that in the
report.
Method
- Read the vendored changelog. It is under
remote-docs/code.claude.com/docs/en/(hooks-daemon remote-docs listnames it;.claude/REMOTE-DOCS.mdis the index). Read every version entry in the range, FROM exclusive, TO inclusive. If the copy does not reach TO, stop and say so; do not review from memory. - Pick the relevant changes. A change is relevant when it touches something the daemon
owns or depends on:
- hook events, payload fields, exit codes and decision semantics;
- compaction, context and prompt-cache behaviour, and usage or rate limits;
- permissions and permission modes, settings, plugins, subagents and worktrees;
- session start, resume and the status line.
- Check the daemon's side. For each relevant change, grep this repository for the
handler, setting or document that overlaps it (pass
--exclude-dir=cyber-flag, never searchuntracked/). A classification with nofile:linefor the daemon side is unfinished. - Classify each relevant change as exactly one of:
- adopt: the daemon should use it;
- redundant: the daemon duplicates it;
- conflict: the daemon fights it;
- no impact: relevant on its face, nothing to do.
Output
Write the report to the path the caller names. It holds:
- The range reviewed, the changelog copy's
fetched_at, and any gap. - A table: version, quoted change, class, daemon-side
file:line, and the action. - For every adopt, redundant or conflict row, a proposed one-line ledger title. Filing the ledger entry is the caller's job, not yours.
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.
- 13d ago First seen · 53 lines · 45 tokens per session scan A 4733b2576472
claude-code-changelog-reviewer is an agent published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (4 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 627 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
scope
IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
implementer
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.
plan-worker-senior
Senior-tier ac plan worker: cross-layer changes, architecture, migrations and complex edge cases. Spawned only by /ac:execute; not for general tasks.
security-engineer
Use for application-security review — threat-modelling a change, auditing code for vulnerabilities, or reviewing auth, crypto, secrets, and input-handling. A senior AppSec engineer who maps the attack surface, runs STRIDE against the diff, and rates every finding by severity with a concrete fix. Pick this for any…
release-cross-review
Policy-derived cross-vendor reviewer for bounded release slices and goal evidence.