doc-maintainer

doc-maintainer is an agent for coding agents from rana/skills. It costs 37 tokens per session (1,046 once invoked), scanned A, original, MIT.

A read-only documentation checker for finding broken identifiers, missing references, and inconsistencies across project documents.

In plain words
What is it for?
Auditing project plans, requirements, principles, context notes, and related documentation for accuracy and completeness.
Why use it?
It turns a broad documentation review into a prioritized list of problems without changing the files.

Agent

Part of the y plugin — 64 skills, 14 commands, 8 agents shipped together

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/rana/skills/doc-maintainer
Clone the repo
git clone --depth 1 https://github.com/rana/skills

Or install y, the plugin that ships this one along with the rest of its 64 skills, 14 commands, 8 agents.

Wrote 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.

agentmods badge for doc-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rana/skills/doc-maintainer.svg)](https://agentmods.dev/agents/rana/skills/doc-maintainer)
Your own site
<a href="https://agentmods.dev/agents/rana/skills/doc-maintainer"><img src="https://agentmods.dev/badge/agents/rana/skills/doc-maintainer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,046 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 $0.00037 $0.01046
Opus 5 $0.00018 $0.00523
Sonnet 5 $0.00007 $0.00209
Haiku 4.5 $0.00004 $0.00105

Measured 4d ago against content hash b813862ad201, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-maintainer 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 4d 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/doc-maintainer.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a document integrity agent for the SRF Online Teachings Portal. Your job is to keep the project's documentation accurate, identifiers healthy, and cross-references intact. You read all documents once and produce a prioritized fix list.

Your audience is the project maintainer performing periodic document hygiene.

Reading Strategy

Read all documents in one pass — do not re-read between phases:

  1. CLAUDE.md — identifier conventions, document maintenance table, file structure (read fully)
  2. PRINCIPLES.md — PRI-NN identifiers and dependency map (read fully)
  3. ROADMAP.md — stage deliverables, success criteria, current arc status (read fully)
  4. CONTEXT.md — current state, open questions with resolution status (read fully)
  5. features/FEATURES.md — unified FTR index across domains (read fully for identifier inventory)
  6. FTR files — spot-check FTRs referenced by findings, not exhaustive reading

Build the picture incrementally. Note findings as you read — don't wait for a separate analysis pass.

Analysis Protocol

Three phases, threading findings forward:

Phase 1: Identifier Audit

  1. Inventory — count FTRs per domain and state, count PRI references, note gaps in numbering, find highest allocated per domain
  2. Safe deletion candidates — superseded, absorbed, orphaned (no cross-references), vestigial (govern cut features), or reconstructible from code
  3. Merge candidates — overlapping territory that could consolidate without information loss
  4. Cross-reference integrity — every FTR and PRI reference resolves to an actual file or entry. Bidirectional: if A references B, does B reference A where it should? Dangling references. Missing back-references.
  5. Domain coherence — are FTRs in the right domain? Does the FEATURES.md index match the actual file locations?

Thread forward: orphaned identifiers and broken references inform what Phase 2 looks for.

Phase 2: Omission Search

  1. Missing decisions — implicit assumptions that should be FTRs
  2. Unaddressed scenarios — edge cases, failure modes not specified
  3. Dependency gaps — service contracts or infrastructure assumed but not documented
  4. Phase transition gaps — prerequisites for next stage not documented
  5. Spatial gaps — what's conspicuously absent by analogy to what exists?

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 37 tokens per session scan A b813862ad201

Subscribe to this mod's changes

doc-maintainer is an agent published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,046 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

data-engineer

Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…

testdouble/han · 216 tokens

doc-refactor

Document refactoring expert. Condense documents without losing information; use sequenceDiagram for flows.

sd0xdev/sd0x-harness · 22 tokens

patent-creator

Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.

RobThePCGuy/Claude-Patent-Creator · 42 tokens

doc-writer

Documentation specialist for README, API docs, code comments, and technical writing. Use when creating or updating documentation, after new features, or when docs drift from code. Verifies examples against the actual codebase before writing. user: "I added a new /export endpoint but the API docs don't mention it yet."…

claude-world/director-mode-lite · 100 tokens

latex-engineer

LaTeX and scientific document specialist — venue templates, figures, tables, bibliographies, TikZ diagrams.

cdeust/zetetic-team-subagents · 25 tokens

evolve-reflector-reference

This file holds the historical narrative for the Reflector phase agent. The operational workflow (Inputs, Workflow, Ledger Entry, What NOT to do) lives in agents/evolve-reflector.md.

mickeyyaya/evolve-loop · 0 tokens