docs-drift

A read-only audit of whether documentation matches a plugin's upcoming or latest released changes. It checks changelogs, READMEs, project instructions, and other documentation against the selected release window.

In plain words
What is it for?
Use it to audit unreleased changelog entries, review the latest tagged release, or check one plugin's documentation for drift.
Why use it?
It finds claims and instructions that no longer match the code before a release or after one has shipped. It does not edit, commit, tag, push, publish, or release anything.

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/gtapps/claude-code-hermit/docs-drift
Any agent
npx skills add gtapps/claude-code-hermit --skill docs-drift
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code, Codex.

Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,325 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 $0.00170 $0.02325
Opus 5 $0.00085 $0.01162
Sonnet 5 $0.00034 $0.00465
Haiku 4.5 $0.00017 $0.00232

Measured 2d ago against content hash d13bc0d2f8e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-drift 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/skills/docs-drift/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Drift

Verify that documentation tells the truth about either the changes about to ship or the latest version already shipped.

Keep the audit read-only. Do not edit, commit, tag, push, publish, or release until the user explicitly approves specific findings. Even after approval, never commit or publish from this skill.

Invocation

  • $docs-drift or $docs-drift unreleased — audit every plugin with a non-empty [Unreleased] section.
  • $docs-drift <plugin-slug> — audit that plugin's unreleased changes.
  • $docs-drift latest — audit the latest reachable release of every tagged plugin.
  • $docs-drift latest <plugin-slug> — audit only that plugin's latest release.

Use unreleased mode by default. Treat "latest version", "latest release", or equivalent wording as latest-release mode.

Typical release order, when the sibling skills are installed:

$release-status$pre-release-review$docs-drift$release

Step 1 — Scope plugins and snapshots

Never mix released and unreleased windows in one claim set.

Unreleased mode

Identify plugins whose [Unreleased] section contains non-blank content:

for p in plugins/*/CHANGELOG.md; do
  slug=$(basename "$(dirname "$p")")
  awk '/^## \[Unreleased\]/{f=1; next} /^## \[/{f=0} f && NF' "$p" | rg -q '.' \
    && echo "$slug"
done

If the user named a plugin, limit scope to that slug after verifying it exists and has unreleased content. If nothing is in scope, stop with:

No unreleased changes in any plugin — nothing to drift-check.

Use the working tree as the documentation snapshot. Keep incidentally noticed older drift separate as pre-existing debt.

Latest-release mode

Start from all plugins/*/CHANGELOG.md slugs, or only the user-named slug. Resolve each plugin's refs independently:

EMPTY_TREE=$(git hash-object -t tree /dev/null)

for p in plugins/*/CHANGELOG.md; do
  slug=$(basename "$(dirname "$p")")
  latest=$(git describe --tags --abbrev=0 --match "${slug}--v*" HEAD 2>/dev/null || true)

  if [ -z "$latest" ]; then
    printf '%s\n' "$slug: skipped (no reachable release tag)"
    continue
  fi

  previous=$(git describe --tags --abbrev=0 --match "${slug}--v*" "${latest}^" 2>/dev/null || true)
  printf '%s\n' "$slug latest=$latest previous=${previous:-<empty-tree>}"
done

Read the full file on GitHub · 254 lines

Files

What ships with it

1 file 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 · 254 lines · 170 tokens per session scan A d13bc0d2f8e9

Subscribe to this mod's changes

docs-drift is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 170 tokens to every session and 2,325 once invoked, about $0.0009 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens