update-docs

A documentation-sync skill that compares code changes with the README, guides, schemas, examples, and other documentation that describe them.

In plain words
What is it for?
Use it after code changes, when a stop check reports missing documentation, or before committing changes that affect documented behavior.
Why use it?
It helps prevent documentation from becoming inconsistent with new or changed code, including configuration, endpoints, errors, security, and deployment details.

Skill for Claude CodeCodex

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/fold-run/fold/update-docs
Any agent
npx skills add fold-run/fold --skill update-docs
Clone the repo
git clone --depth 1 https://github.com/fold-run/fold

Made for: Claude Code, Codex.

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 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 $0.00073 $0.00620
Opus 5 $0.00036 $0.00310
Sonnet 5 $0.00015 $0.00124
Haiku 4.5 $0.00007 $0.00062

Measured yesterday against content hash 2af788a36ae0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-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 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.

.claude/skills/update-docs/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update fold's docs from the working diff

Documentation drift is a merge-blocker in spirit here: README sections track code directly, and the schema drift test makes part of it literal. This skill turns "the diff changed behavior" into "the right doc surfaces changed with it".

1. Scope the drift

git diff --name-only HEAD    # plus: git ls-files --others --exclude-standard

Map changed code to the surfaces that track it:

Changed Doc surface that must keep up
gateway/router.go middleware order README "Request pipeline"
config/config.go fields config/fold.config.schema.json (drift test), docs/configuration.md, docs/defaults.md, fold.config.example.json, and the README's config summary table if a whole section is added or removed
Minted error codes README "Error codes"
New/changed endpoints, metrics README "Operational endpoints" / "Observability", docs/operations.md
Auth, policy, EMA docs/security-model.md, docs/configuration.md auth/policy sections
Embedding API (gateway.New/Reload/Handler) docs/embedding.md, README "API stability"
Deploy artifacts (Dockerfile, deploy/, compose) docs/deploy.md, README "Deploying"
Closing/widening a deliberate gap README "Not implemented"
Architectural invariants (snapshot, sessions, pipeline) CLAUDE.md

Not doc-relevant: *_test.go-only changes, .claude/ changes, pure refactors with no observable behavior change — say so and stop.

2. Delegate to the docs-sync agent

For anything beyond a one-line fix, launch the docs-sync subagent with: the list of changed files, a one-paragraph summary of the behavior change, and the specific surfaces from the table above it should audit. It verifies claims against code and edits the docs; relay its report.

Trivial single-surface fixes (one README line) may be done inline.

3. Verify

  • Schema or example config touched → go test ./config.
  • CHANGELOG.md is release-time only — never add entries there for unreleased work (that happens in /fold-release step 3).
  • Report: surfaces updated, surfaces checked-and-already-accurate, and anything deliberately deferred (e.g. changelog).

Read the full file on GitHub · 52 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. yesterday First seen · 52 lines · 73 tokens per session scan A 2af788a36ae0

Subscribe to this mod's changes

update-docs is a skill published in the GitHub repository fold-run/fold (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 620 once invoked, about $0.0004 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.