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 instructions/recailai/jockey/agents-mdgit clone --depth 1 https://github.com/recailai/jockeyWrote 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/instructions/recailai/jockey/agents-md)<a href="https://agentmods.dev/instructions/recailai/jockey/agents-md"><img src="https://agentmods.dev/badge/instructions/recailai/jockey/agents-md.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 | $0.00587 | $0.00587 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
jockey AGENTS.md 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/: SolidJS + TypeScript UI (App.tsxis the main view entry,index.tsxbootstraps app,index.cssholds Tailwind/CSS variables).src-tauri/src/: Rust backend for Tauri commands and orchestration logic (lib.rsandacp.rs).docs/: Architecture notes and RFC-style design docs.public/: Static assets packaged by Vite.- Generated output:
dist/(frontend build) andsrc-tauri/target/(Rust build artifacts); do not commit these.
Build, Test, and Development Commands
pnpm dev: Run Vite dev server for frontend iteration.pnpm tauri dev: Run the full desktop app (frontend + Rust backend hot reload).pnpm build: Build production frontend assets intodist/.pnpm tauri build: Build distributable desktop bundles.cargo check --manifest-path src-tauri/Cargo.toml: Fast Rust type check.cargo test --manifest-path src-tauri/Cargo.toml: Run Rust tests.cargo clippy --manifest-path src-tauri/Cargo.toml: Rust lint checks.cargo fmt --manifest-path src-tauri/Cargo.toml: Format Rust code.
Coding Style & Naming Conventions
- TypeScript/Solid: use 2-space indentation, semicolons,
camelCasefor variables/functions,PascalCasefor components and type names. - Rust: rely on
rustfmtdefaults (4-space indentation),snake_casefor functions/variables,CamelCasefor structs/enums. - Keep Tauri command payloads and frontend types in
camelCaseto match existing serde usage (#[serde(rename_all = "camelCase")]). - Prefer small, focused modules; place protocol/backend logic in
src-tauri/src/and UI behavior insrc/.
Testing Guidelines
- Primary automated tests are currently Rust-side via
cargo test. - Add unit tests next to Rust modules when introducing non-trivial logic.
- Frontend test framework is not configured yet; include manual verification steps in PRs (for example: team creation, role binding, assistant chat flow).
Commit & Pull Request Guidelines
- Follow Conventional Commits, as seen in history:
feat: ...,docs: ...,chore: .... - Keep commits scoped to one change theme; use imperative, specific summaries.
- PRs should include:
- concise problem/solution description,
- linked issue (if available),
- testing evidence (
cargo test,pnpm build, manual UI checks), - screenshots or short recordings for UI changes.
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 · 39 lines · 587 tokens per session scan A d8bcb056c237
jockey AGENTS.md is an instructions file published in the GitHub repository recailai/jockey (24 stars, last pushed 3mo ago), licensed MIT. It adds 587 tokens to every session, about $0.0029 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 instructions, from other repositories
Clutch CLAUDE.md
Claude Code instructions for fancy1108/Clutch, covering 📍 项目定位, ⛔ 铁律, ⚡ 核心命令, 🔄 long-running agent 规则 and layer 4 操作剧本（.claude/workflows/、.cursor/）.
Meldwork AGENTS.md
AGENTS.md instructions for Ryder-MHumble/Meldwork, covering meldwork development rules, working style, product boundaries, frontend and desktop and verification.
Clutch copilot-instructions.md
Copilot instructions for fancy1108/Clutch, a project described as: Local AI multi-agent orchestration desktop app (Tauri · LangGraph).
rovai-ai AGENTS.md
AGENTS.md instructions for murray17/rovai-ai, covering agents.md, project documentation and frontend design.
wayland AGENTS.md
AGENTS.md instructions for FerroxLabs/wayland, covering coordination (read every task — multi-agent blackboard), wayland - project guide, code conventions, file & directory structure and naming.
wayland copilot-instructions.md
Copilot instructions for FerroxLabs/wayland, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.