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 paulbaranowski/wild-horses/plugin install plain-languageWrote 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/commands/paulbaranowski/wild-horses/check)<a href="https://agentmods.dev/commands/paulbaranowski/wild-horses/check"><img src="https://agentmods.dev/badge/commands/paulbaranowski/wild-horses/check.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 | $0.00038 | $0.00737 |
| Opus 5 | $0.00019 | $0.00368 |
| Sonnet 5 | $0.00008 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
check 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plain-language: check
Report where prose breaks the plain-language standard. This command never edits a file.
Bundled assets at ${CLAUDE_PLUGIN_ROOT:-${CURSOR_PLUGIN_ROOT}}. If the variable is not substituted
in this context, find the files with Glob "**/plain-language/standard.md"
and read the siblings alongside it.
standard.md- the writing standard.scope.md- scope resolution, the extension table, the changed-lines map.scripts/plain_language_cli.py- the deterministic scanner.
Target: "$ARGUMENTS"
Steps
-
Resolve the scope with
scope.md. The result is a file list, a file list plus a changed-lines map, or free text. -
Free text: check it against
standard.mdyourself. List each violation with its sentence in the reply. Stop here. -
Run the scanner:
python3 "${CLAUDE_PLUGIN_ROOT:-${CURSOR_PLUGIN_ROOT}}/scripts/plain_language_cli.py" scan FILE...For PR scope, add
--changed-lines -and pipe the map perscope.md. -
Judge every candidate hit against
standard.md, including its "What not to flag" section. Six kinds are candidates, not verdicts:banned-token: read the sentence and decide literal or figurative. Literal uses pass. Figurative uses are violations.filler-phrase: a violation when the phrase carries no fact. It passes when the sentence needs those words.copula-avoidance: a violation when "is", "are", or "has" says the same thing. It passes when the verb carries real meaning.empty-phrase: a violation when the phrase promises depth and names nothing. It passes when the sentence goes on to name the thing.dash-substitute: a violation when the character does an em-dash's job. A number range passes.diff-anchored: a violation when the prose narrates a change the reader cannot see. It passes in a changelog, a release note, or a migration guide, because those documents are about a change.
-
Report in this order. First the totals by kind. Then, per file, each violation with its line number and sentence. Then the candidate hits you judged correct and left, grouped by kind. Then the files skipped, with reasons, and the blocks skipped, grouped by reason. Last, any parse errors.
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.
- 7d ago First seen · 67 lines · 38 tokens per session scan A 2910817add58
check is a command published in the GitHub repository paulbaranowski/wild-horses (11 stars, last pushed 19d ago), licensed MIT. It adds 38 tokens to every session and 737 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.