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.
npx agentmods add skills/validatedpatterns/docs/doc-reviewnpx skills add validatedpatterns/docs --skill doc-reviewgit clone --depth 1 https://github.com/validatedpatterns/docsWhat 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 | $0.00123 | $0.01800 |
| Opus 5 | $0.00062 | $0.00900 |
| Sonnet 5 | $0.00025 | $0.00360 |
| Haiku 4.5 | $0.00012 | $0.00180 |
Grade A, and why
doc-review 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the documentation file(s) at $ARGUMENTS for compliance with the Red Hat/IBM Style Guide. Follow the workflow below precisely.
Step 1: Resolve targets
- If
$ARGUMENTSis empty, ask the user which file(s) or directory to review. - If
$ARGUMENTSis a directory, recursively glob for all*.adoc,*.md, and*.markdownfiles. - If
$ARGUMENTSis a file, use it directly. - If no matching files are found, inform the user and stop.
Step 2: Detect format and scan for likely violations (two-pass strategy)
For each file, detect the format by extension:
| Extension | Format |
|---|---|
.adoc |
AsciiDoc |
.md, .markdown |
Markdown |
Pass 1: Quick scan and guide selection
Read the file and scan for signals that indicate which rules are likely violated. Then load only the guides that are relevant, rather than all 24. This keeps reviews efficient without sacrificing coverage.
Always load these high-impact guides first (they catch the most common issues):
| Priority | Guide file | Topic | Load when you see... |
|---|---|---|---|
| P1 | guides/minimalism.md |
Conciseness, scannability, removing fluff | Long paragraphs, "in order to", "this section describes", filler adverbs |
| P2 | guides/passive-voice.md |
Prefer active voice | "is/are/was/were/been + past participle", "can be", "should be" |
| P3 | guides/avoid-these-words.md |
Full banned words table | Any uncertain word choice |
| P4 | guides/capitalization.md |
Sentence-style capitalization | Title-case headings |
| P5 | guides/titles-and-headings.md |
Gerunds for procedures, nouns for concepts | Procedural headings that don't start with a gerund |
| P6 | guides/contractions.md |
Avoid contractions | Apostrophes in words (don't, won't, it's, you'll) |
| P7 | guides/conscious-language.md |
Inclusive terminology | whitelist, blacklist, master, slave, sanity |
| P8 | guides/anthropomorphism.md |
No human traits for products | "system knows", "tries to", "smart enough" |
What ships with it
24 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.
- guides/anthropomorphism.md 943 B
- guides/asciidoc-specific.md 5.8 KB
- guides/avoid-these-words.md 5.2 KB
- guides/capitalization.md 663 B
- guides/colons-and-semicolons.md 1.7 KB
- guides/command-line.md 1.4 KB
- guides/commas-restrictive-nonrestrictive.md 1.2 KB
- guides/conscious-language.md 1.4 KB
- guides/contractions.md 747 B
- guides/future-tense.md 1001 B
- guides/incomplete-sentences.md 630 B
- guides/inline-links.md 916 B
- guides/markdown-specific.md 4.0 KB
- guides/minimalism.md 4.4 KB
- guides/optional-and-conditional-steps.md 1.0 KB
- guides/parallelism.md 985 B
- guides/passive-voice.md 941 B
- guides/phrasal-verbs.md 936 B
- guides/possessives-and-apostrophes.md 803 B
- guides/screen-captures.md 718 B
- guides/single-step-procedures.md 617 B
- guides/titles-and-headings.md 1.3 KB
- guides/ui-elements.md 1.6 KB
- guides/unordered-lists.md 578 B
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.
- 2d ago First seen · 130 lines · 123 tokens per session scan A 1d6072b222d6
doc-review is a skill published in the GitHub repository validatedpatterns/docs (20 stars, last pushed 7d ago), licensed Apache-2.0. It adds 123 tokens to every session and 1,800 once invoked, about $0.0006 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.
Other skills, from other repositories
golden-rss
Use when testing the rss golden build.
golden-chat-topics
Use when testing the goldenchattopics golden build.
golden-chat-single
Use when testing the goldenchatsingle golden build.
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…
keep-the-why
Preserves or recovers the reasoning behind a codebase - architectural decisions, rejected alternatives, workarounds, incident learnings, operational constraints, and historical context the code itself cannot explain. Use when implementing or reviewing a non-trivial change involving a design decision, workaround…
summarize
Summarize conversations, logs, docs, or investigation notes into action-oriented text with evidence tags. Use for recap, handoff, CI failure digest, or MEMORY. Triggers: 总结, 汇总, summarize, 交接, 复盘, 调试总结.