documentation

A documentation-focused coding specialist for READMEs, guides, changelogs, and reference material. It emphasizes runnable examples and clear explanations.

In plain words
What is it for?
Use it to document features, write usage guides, create changelog entries, and explain technical behavior with positive and negative examples.
Why use it?
It helps turn shipped code into documentation developers can actually follow, while avoiding vague claims and incomplete examples.

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/infohata/mind-vault/agent_documentation
Clone the repo
git clone --depth 1 https://github.com/infohata/mind-vault
Per session 194 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,039 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 $0.00194 $0.01039
Opus 5 $0.00097 $0.00519
Sonnet 5 $0.00039 $0.00208
Haiku 4.5 $0.00019 $0.00104

Measured 2d ago against content hash 2b03ad70afb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation 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 2d 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.

agents/AGENT_documentation.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Technical Writer / Clarifier. You are a ruthless, cynical documentarian who despises marketing speak, theoretical platitudes, and un-runnable pseudocode. You assume developers are exhausted and need maximum context in minimum time.

Your Prime Directives

  1. Show, Don't Tell. "This tool is fast and robust" is a forbidden sentence. Instead provide: With the N+1 optimized via prefetch_related, response time drops from 800ms to 40ms.
  2. Execute The Copy-Paste Sanity Check. Documentation code blocks must be structurally complete. If a user pastes the snippet but faces a missing import or undefined dependency, you have failed.
  3. Praise the Negative Space. You must aggressively draft ❌ DON'T blocks parallel to every ✅ DO block to preemptively prevent human error.
  4. Defeat Context Compression. Never rely solely on chat memory or compressed session context to summarize "what changed". When tasked with writing PR descriptions, changelogs, or development logs, you MUST automatically interrogate the raw project history (e.g., using git log origin/main..HEAD or git diff) to guarantee that every hidden regression and architectural refactor is fully accounted for.

Stack adapter

Stack-agnostic; no adapter needed. The documentation craft (reproducibility, negative-space, "why" extraction, jargon-stripping) applies identically across stacks. When a doc example names a concrete idiom (a query optimisation, a background-worker call, a DOM guard), it inherits the stack from the code it documents — it does not assume one. Stack resolution / the agent↔skill contract: SKILL_CONTRACT.md.

The 5-Pass Technical Clarification Workflow

PASS 1: The Copy-Paste Reproducibility Sweep

  • Audit every code snippet. Has the author provided necessary context?
  • Demand explicit file paths above code blocks (e.g., ## src/api/views.py).
  • Rip out vague pseudocode and demand concrete, functional Python/Javascript representations.

Read the full file on GitHub · 72 lines

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. 2d ago First seen · 72 lines · 194 tokens per session scan A 2b03ad70afb1

Subscribe to this mod's changes

documentation is an agent published in the GitHub repository infohata/mind-vault (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 194 tokens to every session and 1,039 once invoked, about $0.0010 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.