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 commands/paulbaranowski/wild-horses/installgit clone --depth 1 https://github.com/paulbaranowski/wild-horsesWrote 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/install)<a href="https://agentmods.dev/commands/paulbaranowski/wild-horses/install"><img src="https://agentmods.dev/badge/commands/paulbaranowski/wild-horses/install.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 | $0.00054 | $0.01115 |
| Opus 5 | $0.00027 | $0.00558 |
| Sonnet 5 | $0.00011 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
install 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linting Hooks — Install
Set up the PostToolUse hooks bundled with this plugin. Hook registration is automatic (via hooks/hooks.json merged on plugin enable). Scripts silently no-op until their dependencies are installed — so a hook is inert on a fresh install and becomes active once the right software is on PATH.
This command is the opt-in surface for which hooks the user wants functional and what software to install to make that so.
Bundled hooks
| Hook | When it fires | What it does | Dependencies |
|---|---|---|---|
markdown-combo-fix |
PostToolUse on Edit|Write|MultiEdit for .md |
Runs prettier --write then markdownlint-cli2 --fix on the edited file. Non-blocking. |
jq, prettier, markdownlint-cli2 |
pyright-post-edit |
PostToolUse on Edit|Write|MultiEdit for .py |
Runs pyright <file> and prints findings to stderr. Non-blocking — never blocks the edit. |
jq, pyright |
Each script self-guards: if required tools are missing, it exits 0 without output.
Phase 1 — Present the options and ask
Show the table above to the user. Then use AskUserQuestion with multiSelect: true:
- Question: "Which linting hooks should be functional on this machine? (Hooks are already registered; this picks which ones get their software installed.)"
- Header: "Hooks"
- Options (one per bundled hook above) — label is the hook name, description summarises its behavior + deps.
If the user picks nothing, stop cleanly: "No hooks selected — nothing to install. The hooks stay registered but dormant."
Phase 2 — Detect missing tools
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.
- 6d ago First seen · 101 lines · 54 tokens per session scan A f9ca8ae02379
install is a command published in the GitHub repository paulbaranowski/wild-horses (11 stars, last pushed 18d ago), licensed MIT. It adds 54 tokens to every session and 1,115 once invoked, about $0.0003 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.