Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install dev-workflowsWrote 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/agents/ihudak/ihudak-claude-plugins/docs-style-checker)<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/docs-style-checker"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/docs-style-checker.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00128 | $0.03750 |
| Opus 5 | $0.00064 | $0.01875 |
| Sonnet 5 | $0.00026 | $0.00750 |
| Haiku 4.5 | $0.00013 | $0.00375 |
Grade A, and why
docs-style-checker 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 3d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the docs repo's project-configured prose linter on a set of files, and ALSO (when available) run prose-style-checker as a complementary semantic / cross-page-consistency pass. Merge and dedupe their findings into a single reviewer finding schema.
Invoked from /document (keyed mode, Phase 6.4) and /document (direct mode, Phase 3.5), after the files are written and before doc-reviewer. Catching corporate-style issues locally frees the doc-reviewer (Opus) to spend its attention budget on correctness and completeness rather than prose policing, and ensures the eventual PR doesn't bounce on CI style checks.
Rationale
Corporate style guides (Microsoft, Google, and various organisation-specific variants) are encoded as Vale style packages maintained by each organisation's docs team, not by this plugin. The docs repo references them via .vale.ini (BasedOnStyles = …). Re-encoding or crawling the corporate style-guide site would duplicate the canonical source and drift. Wrapping the repo's existing tooling guarantees the local check matches what CI will run on the PR.
Why ALSO run prose-style-checker when a primary linter is available (since v1.7.1): empirical verification showed the two are complementary, not overlapping:
| Class of finding | Vale catches | prose-style-checker catches |
|---|---|---|
| Lexical (banned words, contractions, hyphens) | ✅ at scale | partial |
| Em-dash spacing, sentence length | ✅ | ✅ |
Missing frontmatter fields (navigation:, title length) |
✅ | ❌ |
Engineer jargon (latest-minus-one, LTS-1) |
❌ no rule | ✅ MAJOR |
| Cross-page label consistency (e.g. "Settings > Updates" across N pages) | ❌ | ✅ MAJOR |
| Subject-verb agreement, misplaced modifier | ❌ | ✅ MINOR |
Plural/singular UI-label mismatch (update window vs update windows) |
❌ | ✅ MAJOR |
Running ONLY the primary linter (because it exists) misses the semantic / cross-page class. Running ONLY prose-style-checker duplicates work and is slower at lexical. Chaining both — primary first, prose-style-checker complementary — covers both classes without rework.
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.
- 3d ago Changed a1a357b667a5
- 8d ago First seen · 163 lines · 128 tokens per session scan A c8cec1001679
docs-style-checker is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 5d ago), licensed MIT. It adds 128 tokens to every session and 3,750 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.
code-filter
Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
meeting-organizer
Prepare and summarize meeting docs.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.