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.
git clone --depth 1 https://github.com/Rune-kit/runeWrote 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/rune-kit/rune/cook)<a href="https://agentmods.dev/agents/rune-kit/rune/cook"><img src="https://agentmods.dev/badge/agents/rune-kit/rune/cook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/rune-kit/rune/cook"><img src="https://agentmods.dev/badge/agents/rune-kit/rune/cook.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.00676 |
| Opus 5.5 | $0.00018 | $0.00270 |
| Sonnet 5.5 | $0.00009 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
cook 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the cook skill — Rune's primary implementation orchestrator.
Step 0 — Prerequisite Check (BEFORE starting work)
- Plan exists? Check for
.rune/plan-*.mdor approved plan in conversation. If non-trivial task (3+ files or significant logic) and NO plan → invokerune:planfirst, wait for user approval, then return here. - Codebase scanned? Check if scout has run. If no codebase context → invoke
rune:scoutto gather structure before Phase 1. - Contract loaded? Check for
.rune/contract.md. If exists, load and enforce throughout. - Resume check? Check for
.rune/plan-*-phase*.mdor.continue-here.md→ resume from last checkpoint.
Only proceed to Phase 1 after Step 0 is satisfied.
Quick Reference
8-Phase Workflow (scaled by rigor assessment):
- Understand — scout codebase, run BA for requirements, clarify scope (max 2 questions)
- Plan — create implementation plan; user MUST approve before proceeding
- Test (RED) — write failing tests first (happy path + edge cases)
- Implement (GREEN) — code to pass tests; max 3 debug loops, 1 replan
- Quality — Stage 1: preflight + sentinel (parallel) → Stage 2: review + completion-gate (parallel)
- Verify — lint + types + tests + build ALL green
- Commit — semantic git commit via git skill
- Bridge — save decisions, progress, conventions for next session
Rigor Levels (auto-assessed from risk signals):
- Nano (0 risk) → DO → VERIFY → DONE (≤3 steps, no logic)
- Fast (1-2) → Understand → Implement → Verify → Commit
- Standard (3-5) → All phases except adversary
- Full (6-8) → All phases including adversary red-team
- Critical (9+) → All phases + sentinel@opus + adversary
Hard Gates:
- Scout BEFORE planning — no guessing codebase structure
- User MUST approve plan before writing tests
- Tests MUST fail before implementation (TDD red-first)
- ALL tests green before commit — zero exceptions
- 5+ consecutive reads without a write = STUCK → act or report BLOCKED
- Contract violations (
.rune/contract.md) are non-negotiable
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.
- 1mo ago First seen · 49 lines · 46 tokens per session scan A b7ac010c2a1e
cook is an agent published in the GitHub repository Rune-kit/rune (86 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 676 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Typical triggers include the user asking whether tests on a freshly-created PR are thorough…
implementer-agent
Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.
senior-dev
Senior developer for test-first implementation. Use for implementing features or bugfixes through strict red-green-refactor TDD. Follows the test-driven-development skill.
quality-guardian
MANDATORY specialist subagent for Testing, Security Hardening, TDD Debugging, and Anti-Slop Auditing. Delegate to this subagent to verify builds, execute test suites, audit code quality, or run security red-teaming before production release.
implement-executor
Executes one task or a bounded batch of up to four tasks using strict TDD red-green-refactor. Writes failing tests first, verifies they FAIL, then writes minimum implementation to pass, then refactors. Receives ordered tasks, ownership, PROJECTCOMMANDS, and TDD protocol from the orchestrator. Returns per-task…
orc-implementer
Executor role — senior-developer agent that implements a defined slice list from a plan + failing test(s). Receives 1 or N slice IDs from the caller; drives each through the TDD red-green-refactor cycle, commits per slice via orc:git-commit, runs the full suite between slices. Default executor in /orc:flow Phase 5…