Borrowing it
Nothing to install: this file belongs to gke-labs/kube-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gke-labs/kube-agents/main/.agents/skills/review-docs-drift/SKILL.mdgit clone --depth 1 https://github.com/gke-labs/kube-agentsWrote 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.
[](https://agentmods.dev/skills/gke-labs/kube-agents/review-docs-drift)<a href="https://agentmods.dev/skills/gke-labs/kube-agents/review-docs-drift"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/review-docs-drift/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gke-labs/kube-agents/review-docs-drift"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/review-docs-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 75 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 85 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.02303 |
| Opus 5.5 | $0.00018 | $0.00921 |
| Sonnet 5.5 | $0.00009 | $0.00461 |
| Haiku 4.5 | $0.00004 | $0.00230 |
Grade A, and why
review-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 19d 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Given a pull request (a branch diff against main), determine whether the repository's documentation is still accurate after the change, and report exactly which documents need updating and why. You are checking two directions:
- Code → docs: the PR changed behavior, names, defaults, paths, or structure that some document states as fact.
- Docs → source: the PR changed documentation, and what it now says must match the source of truth, the repo's documentation rules, and the other docs.
Your two navigation instruments are:
AGENTS.md(repo root) — owns the documentation RULES: the canonical-home table (one home per fact), the generated-region rule, link-don't-summarise, no PR-status prose, verify-identifiers-against-source.docs/README.md— the documentation MAP: what lives where (a directory tree), which files carry generated regions and from which sources, and which source files own the identifiers that docs state as fact. It carries no per-document rows; what a document covers is the document's own business.
This skill deliberately holds no repository facts of its own — no file lists, no agent topology, no counts. Facts live in the two instruments above and in the sources they point to; when this skill and a source disagree, the source wins and this skill needs fixing.
Read both before reviewing the diff.
Procedure
1. Collect the change surface
git diff --stat main...HEAD(or the PR's base) — list every changed file.- Classify each changed path:
- Source of a generated region? Check the generated-regions table in the map (
docs/README.md§2). If the changed file — or its frontmatter or comment banner — feeds a generated region, that region must be regenerated (make docs-generate) and committed. - Source of documented identifiers? Check the identifier-sources table in the map (
docs/README.md§2). If the changed file owns names, defaults, versions, section numbering, or baked paths that docs state as fact, find every doc that states a fact about the changed item. - Doc file? → review it under step 3.
- Anything else (code, scripts, workflows, examples) → find the pages that describe that component (step 2).
- Source of a generated region? Check the generated-regions table in the map (
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.
- 19d ago Changed 3110363d1bfa
- 1mo ago Changed · +1 lines 9cef5cff5062
- 1mo ago Changed cdb114e779a2
- 1mo ago First seen · 86 lines · 44 tokens per session scan A d624339f465a
review-docs-drift is a skill published in the GitHub repository gke-labs/kube-agents (116 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 2,303 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…