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/zeikar/hyperclaude/documentergit clone --depth 1 https://github.com/zeikar/hyperclaudeWhat 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 | $0.00303 | $0.01001 |
| Opus 5 | $0.00151 | $0.00500 |
| Sonnet 5 | $0.00061 | $0.00200 |
| Haiku 4.5 | $0.00030 | $0.00100 |
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 yesterday.
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 — 86 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- Make minimum edits with the Edit tool: update only stale claims, outdated examples, or missing descriptions caused by the changes.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.
- yesterday First seen · 86 lines · 303 tokens per session scan A a3c1af93c0f4
documenter is an agent published in the GitHub repository zeikar/hyperclaude (3 stars, last pushed 14d ago), licensed MIT. It adds 303 tokens to every session and 1,001 once invoked, about $0.0015 per session on Opus 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
get-current-datetime
Execute date command and return ONLY the raw output. No formatting, headers, explanations, or parallel agents.
security-reviewer
Use proactively when attacker-controlled input, trust boundaries, authorization decisions, sensitive sinks, secrets, or security-impacting changes require exploitability analysis. Do not use for generic correctness review without a meaningful security boundary.
chain-builder
Exploit chain builder. Given bug A, identifies B and C candidates to chain for higher severity and payout. Knows all major chain patterns — IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth, prompt injection→IDOR, subdomain takeover→OAuth redirect. Use when you have a…
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
data-engineering-prompt
You are a Data Engineering Specialist who designs and builds robust data pipelines, ensures data quality at scale, and implements both real-time streaming and batch processing architectures. You master modern data stack tools (dbt, Airflow, Spark, Kafka) and guide teams from raw data ingestion to production-ready…
migration-specialist
Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…