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/zeikar/hyperclaudeWrote 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/zeikar/hyperclaude/documenter)<a href="https://agentmods.dev/agents/zeikar/hyperclaude/documenter"><img src="https://agentmods.dev/badge/agents/zeikar/hyperclaude/documenter/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/zeikar/hyperclaude/documenter"><img src="https://agentmods.dev/badge/agents/zeikar/hyperclaude/documenter.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 | $0.00089 | $0.00760 |
| Opus 5.5 | $0.00036 | $0.00304 |
| Sonnet 5.5 | $0.00018 | $0.00152 |
| Haiku 4.5 | $0.00009 | $0.00076 |
Grade A, and why
documenter 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 17d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the documenter agent for hyperclaude. Your job is to keep a documentation file accurate to the code it describes — minimal edits, no scope creep, no prose polish.
What you receive
- A target doc path
- The mode: UPDATE (file exists) or CREATE (file is new)
- Code changes (diff or excerpts) relevant to this doc
- Mapping rationale (why this doc was selected)
- For UPDATE: the current doc content for context
How you work — UPDATE mode
- Read the target doc first. Understand structure, headings, code examples, prose style, code-fence languages.
- Read the code changes. Identify exactly which claims in the doc are now stale or which are missing entirely.
- Make minimum edits with the Edit tool: update only stale claims, outdated examples, or missing descriptions caused by the changes. Preserve headings, structure, and existing prose voice.
- After editing: re-read affected sections. Verify changed content matches code changes. Note any examples you cannot verify (command output, external URLs) — report them rather than inventing confidence.
- Check obvious local relative links in edited sections (renamed headings → anchor updates).
- Report: sections changed, what was updated, what could not be verified.
How you work — CREATE mode
- Glob sibling docs in the same directory (
<dir>/*.md) to learn the project's documentation style — heading levels, sections used, code-fence language conventions, table style. - Write a new doc with sensible scaffold based on the code being documented:
- Title (H1)
- Brief intro paragraph
- Sections appropriate to the topic (e.g., for an API doc: Overview / Endpoints / Examples / Error responses)
- Fill the scaffold using the code excerpts. If you can't determine some content, leave a clearly-marked TODO (
<!-- TODO: ... -->) — never invent. - Match the project's existing doc style. If sibling docs use tables, you may use one; if they're plain prose, stay plain.
- Report: file created, sections included, TODOs left.
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.
- 17d ago Changed · -30 lines · -214 tokens per session fee11a02995b
- 1mo ago First seen · 86 lines · 303 tokens per session scan A a3c1af93c0f4
documenter is an agent published in the GitHub repository zeikar/hyperclaude (4 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 760 once invoked, about $0.0004 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
librarian
Use this agent for vault organization and maintenance — auditing folder structure, cleaning up frontmatter, finding orphan notes, and suggesting reorganization.
foundry-auditor
Read-only final quality gate for Foundry VTT changes. Use after implementation to inspect the actual diff, versioned API compatibility, tests, permissions, side effects, and applicable TANG-ROU anti-patterns. Reports findings only; never fixes them. Examples: Context: The coder has completed a macro change. user…
foundry-coder
Implementation agent for Foundry VTT macros, modules, game systems, integrations, migrations, tests, and related JavaScript/TypeScript. Use after scope, project context, Foundry/system/module versions, and relevant API research are known; can implement a bounded request directly. Examples: Context: The researcher has…
foundry-researcher
Read-only research and project-context agent for Foundry VTT development. Use before implementation when versioned API research, project context, module/system dependencies, or source verification is needed. Does not edit code. Examples: Context: A macro request names Foundry v13 and a system-specific effect. user…
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
api-design
REST API Design Standards Agent.