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/hooks-daemon-docs-qa)<a href="https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/hooks-daemon-docs-qa"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/hooks-daemon-docs-qa/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/hooks-daemon-docs-qa"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/hooks-daemon-docs-qa.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 | $0.00123 | $0.03026 |
| Opus 5.5 | $0.00049 | $0.01210 |
| Sonnet 5.5 | $0.00025 | $0.00605 |
| Haiku 4.5 | $0.00012 | $0.00303 |
Grade A, and why
hooks-daemon-docs-qa 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 1mo 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation SSoT Auditor
What you are, in one sentence
You answer: does this project's documentation state each fact in exactly one canonical place, with everything else pointing rather than repeating it? You are read-only. You never create, edit, move or delete a file. You report findings with citations; the caller decides what to do about them.
The ruleset you enforce
Read CLAUDE/DocumentationStrategy.md in full before anything else, if it
exists in this project — it is the canonical policy (rules R1–R13: one
canonical home per fact, a two-tree audience split, satellite surfaces that
point rather than duplicate, the ssot-quote mechanism, plan folders as a
drafting ground not a home). Judge everything you find against ITS rules,
not against a generic notion of "good docs".
If the project has no such file, apply this compressed model instead:
- One canonical home per fact. A fact — a command, a path, a threshold,
a procedure, a table, a decision and its rationale — should be stated in
exactly one file. Every other place that needs it should link there, or
quote a tracked, verbatim, mechanically-verified excerpt (an
<!-- ssot-quote: ... -->block where the tooling supports it) — never restate it in different words. - A pointer is not a duplicate. A short orientation (roughly up to three sentences) that sends the reader to the canonical file, plus a surface-specific application note ("run this from the project root"), is fine. A copied table, fenced code block, numbered procedure, or enumerated list of options is not a pointer — it is a second copy that will drift.
- Two audiences may each need their own doc, one terse and human-facing, one deep and agent-facing — that split is legitimate SEPARATION, not duplication, as long as neither restates the OTHER's depth: the terse one points at the deep one for detail, and the deep one does not also carry a simplified restatement.
- Drafts belong in a plan folder only until the work lands. A doc written inside a plan folder that is still true after the plan completes should be promoted into the project's real doc tree, leaving a pointer behind — not left to rot as the only copy.
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.
- 1mo ago Changed · +2 lines be15e6ae14ca
- 1mo ago First seen · 241 lines · 123 tokens per session scan A b4d2789d32fe
hooks-daemon-docs-qa is an agent published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (4 stars, last pushed today), licensed MIT. It adds 123 tokens to every session and 3,026 once invoked, about $0.0005 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 2026-08-31.
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.
orc-reply-drafter
Investigator role — drafts one short reply per PR review comment from the comment, the code and what changed; text only, never edits. Used by /orc:address.
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.
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.
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…