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/apply)<a href="https://agentmods.dev/commands/paulbaranowski/wild-horses/apply"><img src="https://agentmods.dev/badge/commands/paulbaranowski/wild-horses/apply.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 | $0.00045 | $0.01198 |
| Opus 5 | $0.00023 | $0.00599 |
| Sonnet 5 | $0.00009 | $0.00240 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
apply 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plain-language: apply
Rewrite prose until the scanner reports zero long-sentence and em-dash
violations. Code never changes; the verify subcommand proves it.
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- scanner and verifier.
Target: "$ARGUMENTS"
Steps
- Resolve the scope with
scope.md. Free text: rewrite it in the reply perstandard.mdand stop. No files are touched. - Snapshot baselines. For each target file that differs from
HEAD(checkgit status --porcelain), copy it into the scratchpad directory before editing. Clean files use--ref HEADin step 6; snapshotted files use--baseline <copy>. - Run the scanner (with the changed-lines map for PR scope). Files with zero violations are done; count them for the report.
- For each flagged block, read the surrounding file content, then rewrite
the prose:
- Split sentences over 20 words. Never delete a fact the reader would have to rebuild.
- Convert every em-dash (U+2014) in each sentence you rewrite: use a comma, a colon, parentheses, or two sentences.
- Turn passives active where the actor is known.
- Replace figurative banned tokens with the real name. Leave literal uses, and leave hits in blocks the scanner skipped.
- Cut each
filler-phrasehit that carries no fact, or use the short form fromstandard.md. Keep the phrase when the sentence needs those words. - Rewrite each
copula-avoidancehit around "is", "are", or "has". Keep the verb when it carries real meaning. - Replace each
empty-phrasehit with the thing it gestures at. Cut the sentence when no real name exists. - Rewrite each
dash-substitutehit the way you rewrite an em-dash. Leave an en-dash inside a number range. - Rewrite each
diff-anchoredhit to describe the thing as it is now. Leave the hit in a changelog, a release note, or a migration guide. - In code files, edit comment and docstring interiors only. In markdown, never touch fences, inline code, frontmatter, URLs, or table shape.
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 · 95 lines · 45 tokens per session scan A 7dc86d2c3c8a
apply is a command published in the GitHub repository paulbaranowski/wild-horses (11 stars, last pushed 19d ago), licensed MIT. It adds 45 tokens to every session and 1,198 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.