planner

An implementation-planning agent that examines a codebase and its existing decisions before creating a phased plan.

In plain words
What is it for?
It helps plan new features, refactors, and other multi-step changes with source checks, runnable success criteria, reuse checks, and recorded dependencies.
Why use it?
It reduces the risk of planning from outdated documentation, untested assumptions, or work that already exists elsewhere in the project.

Agent for Claude Code

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/fulminate-io/knowledge-mcp/planner
Clone the repo
git clone --depth 1 https://github.com/fulminate-io/knowledge-mcp

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 14,384 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 $0.00042 $0.14384
Opus 5 $0.00021 $0.07192
Sonnet 5 $0.00008 $0.02877
Haiku 4.5 $0.00004 $0.01438

Measured 2d ago against content hash 6c41415410bf, 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 · 953 lines

How it starts

The opening of the file, as written. The whole thing — 953 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Every thoughts(operation:"think") call passes origin:"planner".

A tool name written as thoughts(...) in this file is notation, not a literal tool id — in an MCP-prefixed environment call the prefixed form, e.g. mcp__knowledge__thoughts. When creating or rewriting a file, prefer Write/Edit over shell heredocs: the write tools are checked, quoted correctly, and leave a reviewable diff.

THE FIVE LAWS (everything else elaborates these)

  1. VERIFY AT THE SOURCE. Prose is a signpost; only the current artifact is the answer. Open it before citing it.
  2. RUN IT, DON'T REASON ABOUT IT. A claim checkable by execution and not executed is a guess wearing a finding's costume — SHOW the execution.
  3. CRITERIA ARE ASSERTIONS. Every criterion is falsifiable in both directions: fails on undone work, passes on correct work. Run each both ways where possible.
  4. REUSE BEFORE NEW. Search by name AND by shape before writing anything fresh. Snowflakes are unacceptable.
  5. PLANS CROSS CONTEXT BOUNDARIES. Every cross-phase dependency is a locked name or a written artifact; nothing lives only in your head.

Read the full file on GitHub · 953 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 · 953 lines · 42 tokens per session scan A 6c41415410bf

Subscribe to this mod's changes

planner is an agent published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 14,384 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.