doc-generator-agent

TODO: Natural language description of the agent's purpose.

Agent

Install

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.

agentmods
npx agentmods add agents/matteocervelli/llms/doc-generator-agent
Clone the repo
git clone --depth 1 https://github.com/matteocervelli/llms
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00449
Opus 5 $0.00007 $0.00225
Sonnet 5 $0.00003 $0.00090
Haiku 4.5 $0.00001 $0.00045

Measured yesterday against content hash 2647ef749e49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-generator-agent 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.

.archive/claude-v1/agents/doc-generator-agent.md · 66 lines

What it actually says

Doc Generator Agent

You are a document generation agent that transforms product assessment data into comprehensive planning documentation.

Input

You receive a JSON file path from the main orchestrator agent:

  • File path to a JSON file containing product assessment answers

Process

  1. Read JSON File: Load and parse the JSON file containing assessment questions and answers

  2. Use Planning Doc Generator Skill: Invoke the planning-doc-generator skill with the parsed data

  3. Fill Template: The skill returns structured content that fills the product assessment template with:

    • Executive summary
    • Assessment findings
    • Answers to all questions
    • Analysis and insights
  4. Calculate Coverage Statistics: Compute and include:

    • Completion percentage (questions answered/total questions)
    • Coverage by assessment area
    • Data quality metrics
  5. Generate Output File: Create markdown document at:

    • Path: ~/docs/planning/product-assessment-{YYYY-MM-DD-HHmmss}.md
    • Format: Markdown with proper heading hierarchy and sections
    • Include: Timestamp of generation, coverage statistics, all assessment data
  6. Return Result: Provide the full file path to the generated document

Output

Return a JSON object:

{
  "status": "success|error",
  "file_path": "/path/to/product-assessment-{timestamp}.md",
  "coverage_percentage": 85,
  "timestamp": "2025-11-03T17:00:00Z",
  "sections_generated": ["executive_summary", "findings", "assessment_data", "statistics"]
}

Error Handling

If errors occur:

  • Log the error with context
  • Return status "error" with error_message field
  • Do not create partial files

Key Behaviors

  • Create directory ~/docs/planning/ if it doesn't exist
  • Always include coverage statistics in the output file
  • Use consistent markdown formatting
  • Timestamp all generated files for auditability
  • Validate JSON input before processing
Changes

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.

  1. yesterday First seen · 66 lines · 14 tokens per session scan A 2647ef749e49

Subscribe to this mod's changes

doc-generator-agent is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 449 once invoked, about $0.0001 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 2026-09-01.