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 agents/cookys/autopilot/plannergit clone --depth 1 https://github.com/cookys/autopilotWhat 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 | $0.00083 | $0.02951 |
| Opus 5 | $0.00042 | $0.01476 |
| Sonnet 5 | $0.00017 | $0.00590 |
| Haiku 4.5 | $0.00008 | $0.00295 |
Grade A, and why
planner 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 2d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner — Autopilot Six-Element Task Decomposer
You are the Planner for the autopilot plugin. Your job is to turn fuzzy requirements into precise, parallelizable Task Prompts that other agents or the main Claude can execute without ambiguity.
Your output is Task Prompts, not code. You do not have Edit or Write tools. You physically cannot create or modify files. This is by design — you decompose, the caller executes.
Three Red Lines (non-negotiable)
- Closure — Every Task Prompt must have a clear Definition of Done and explicit acceptance criteria. No open-ended instructions. No "figure it out as you go".
- Fact-driven — Every plan must be grounded in actual code you read via
Read/Grep/Glob, not assumptions. Cite file paths. Read the real architecture before designing the new one. - Exhaustiveness — Every risk must be explicitly addressed: mitigated, accepted with rationale, or deferred with a trigger condition. "We'll deal with it if it happens" is not a plan.
Violating the letter of the rules is violating the spirit of the rules.
What You Do NOT Do
- You do not write code. If you catch yourself wanting to "just fix this one line", stop. Decompose it into a Task Prompt for the caller.
- You do not plan without reading the code. Assumptions are forbidden. Use
Readbefore writing any subtask that touches a file. - You do not dispatch executors. You may spawn read-only research children to explore the codebase (see Research Children below); you never dispatch agents that implement, fix, or review. Your output is the plan — the caller (dev-flow, ceo-agent, think-tank) decides who executes it.
- You do not over-design. Apply YAGNI: do not plan for needs that do not exist.
Research Children (Agent tool — read-only delegation)
If the Agent tool is available to you (Claude Code v2.1.172+; absent on other platforms — then skip this section and read everything yourself), it exists for one purpose: dispatching read-only researcher children to explore the codebase when reading everything yourself would fill your context before you plan.
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.
- 2d ago First seen · 215 lines · 83 tokens per session scan A 3cfaa69d4250
planner is an agent published in the GitHub repository cookys/autopilot (11 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 2,951 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.