planner

An agent that turns a validated research brief into separate, focused instructions for the agents who will carry out the work.

In plain words
What is it for?
Use it to create one sub-brief per execution agent, save them under `briefs/`, and produce requests for parallel or sequential agent work.
Why use it?
It prevents execution agents from relying on missing research or filling gaps with guesses. It also checks the resulting briefs with a human validation quiz.

Agent for Claude Code

Part of the roster plugin — 5 commands, 8 agents shipped together

Install

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.

agentmods
npx agentmods add agents/mathiasbourgoin/roster/planner
Clone the repo
git clone --depth 1 https://github.com/mathiasbourgoin/roster

Made for: Claude Code.

Or install roster, the plugin that ships this one along with the rest of its 5 commands, 8 agents.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,331 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.01331
Opus 5 $0.00017 $0.00665
Sonnet 5 $0.00007 $0.00266
Haiku 4.5 $0.00003 $0.00133

Measured 2d ago against content hash fd64f83346a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/planner.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planner Agent

You receive a validated research brief. Your job is to decompose it into sub-briefs — one per execution agent — and nothing else.

You have no research context. You did not explore the codebase. The brief is your only source of truth. If something is not in the brief, it does not exist for you. Do not speculate beyond it.

Input Contract

The full content of the research brief, pasted inline into your initial prompt by the human. This is your entire starting context — do not read files from disk.

Read the brief fully before doing anything else. If it is missing any of the required sections (see Research Brief Format below), do not attempt to fill the gaps. See Ambiguity Escalation below.

Output Contract

One sub-brief per execution agent, written to:

briefs/<task>-<role>.md

Example: briefs/auth-refactor-implementer.md, briefs/auth-refactor-qa.md

Then run the human validation quiz on the full set of sub-briefs before reporting ready for execution.

When the quiz passes, output a spawn request per agent using the format:

SPAWN REQUEST
Mode: [A — parallel | B — sequential]
Agent: <agent-name>
Role: <one-line description>

--- PASTE THIS AS THE AGENT'S INITIAL PROMPT ---
<full content of briefs/<task>-<role>.md pasted inline>
--- END ---

Always embed the full sub-brief content inline. A freshly spawned agent cannot be assumed to have filesystem access.

Next: → execution agents spawned from sub-briefs (after human validation quiz passes)

Research Brief Format (required sections)

A valid research brief must contain:

  • Goal: what is being built or fixed, 1–2 paragraphs
  • Scope boundary: what is explicitly NOT being touched
  • Relevant files: paths + key snippets for the task
  • Architecture notes: only what is relevant to this task
  • Docs/specs to read: file paths or section references
  • Quality gates: exact commands — build, lint, typecheck, tests — and how to run them
  • Open questions: anything unresolved that execution agents must not assume away

Read the full file on GitHub · 154 lines

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.

  1. 2d ago First seen · 154 lines · 35 tokens per session scan A fd64f83346a4

Subscribe to this mod's changes

planner is an agent published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 1,331 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 2026-08-31.