tend-docs

A documentation-drift checker for repositories that deliberately keep documentation, code artifacts, and API collections in matching reference structures.

In plain words
What is it for?
Use it for periodic repository audits; it identifies and minimally fixes one highest-priority mismatch while leaving application source code untouched.
Why use it?
It finds when documentation lists something that no longer exists, omits something that does, or disagrees with an API collection.

Skill for Claude CodeCodex

Part of the robcsaszar-tend plugin — 7 skills 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 skills/robcsaszar/tend/tend-docs
Any agent
npx skills add robcsaszar/tend --skill tend-docs
Clone the repo
git clone --depth 1 https://github.com/robcsaszar/tend

Made for: Claude Code, Codex.

Or install robcsaszar-tend, the plugin that ships this one along with the rest of its 7 skills.

Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,546 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 $0.00137 $0.01546
Opus 5 $0.00068 $0.00773
Sonnet 5 $0.00027 $0.00309
Haiku 4.5 $0.00014 $0.00155

Measured 2d ago against content hash 7d10c8a574a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tend-docs 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.

skills/tend-docs/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tend Docs — the loremaster

Dogfood-only. This skill assumes the repo already has an explicit doc-reference convention to audit against — a components/API reference doc, an API-contract/collection directory, or paired flow docs describing the same feature from different angles. It's shipped in this pack because it's genuinely useful once a repo has grown that convention, but it's less broadly applicable out of the box than the other tend-* skills — there may be nothing for it to check on a fresh repo.

Find the single highest-priority drift between documentation and real code — a stale doc entry, an undocumented artifact, or an API-contract mismatch — fix it minimally, verify against the ground-truth source, hand back the diff for review. One drift per run.

0. Load config

  • Read .claude/tend/config.yaml if present. Per the config schema, tend-docs has no skills.docs entry — there is nothing repo-specific to read from skills.*. Off-limits are entirely built-in for this skill: the docs tree (and an API-contract directory, if one exists) are the only safe write targets; source/logic directories are never touched, regardless of config presence or content. This skill has no capability modules — skip module-gating entirely.
  • No config file at all changes nothing here — this skill already runs at a fixed, conservative tier by design, not as a fallback.

1. Triage

MANDATORY READ references/scan-core.md.

  • Identify the reference doc(s) that claim to be a source of truth for some set of code artifacts (e.g. a components/API reference file).
  • Identify the real code artifacts to diff against — glob actual files/exports, recursing into subdirectories (the most common blind spot).
  • Identify whether the repo has an API-contract/collection format (Bruno .bru, a Postman collection, an OpenAPI spec, an Insomnia export, etc.) alongside real route/endpoint handlers.
  • Identify any pair or set of docs that describe the same user-facing flow from different angles, and the ground-truth source file that would resolve a contradiction between them.

Read the full file on GitHub · 92 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 92 lines · 137 tokens per session scan A 7d10c8a574a0

Subscribe to this mod's changes

tend-docs is a skill published in the GitHub repository robcsaszar/tend (0 stars, last pushed 3d ago), licensed MIT. It adds 137 tokens to every session and 1,546 once invoked, about $0.0007 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 skills, from other repositories

software-code-refactoring

Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with…

stencila/stencila · 102 tokens

simplify-codebase

Simplification audit or authorized codebase simplification whose stated objective is to remove accidental complexity. Use for evidence-backed deletion or consolidation of dead code, duplicate state, redundant APIs or layers, ownerless abstractions, obsolete compatibility or design records, and over-engineering in any…

tt-a1i/simplify-codebase · 93 tokens

cyclomatic-complexity

Refactor code to reduce cyclomatic complexity so it stays readable, maintainable, and aligned with the long-term vision of the codebase, not just optimized for AI comprehension. Use whenever the user asks to refactor, simplify, clean up, or review code quality; mentions complexity, maintainability, readability…

saurabhkumar8112/cyclomatic-complexity-skill · 103 tokens

refactor

Refactor code to improve structure and maintainability.

vstorm-co/pydantic-deepagents · 12 tokens

absolute-simplify

Use when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on…

maddhruv/absolute · 178 tokens

techdebt

Find and fix technical debt including duplicated code, dead code, outdated patterns, and code smells. Run at the end of sessions to clean up.

brycewang-stanford/Auto-Empirical-Research-Skills · 33 tokens