planner

planner is an agent for coding agents from vasuag09/harness-claude. It costs 52 tokens per session (386 once invoked), scanned A, original, MIT.

A read-only specialist that turns a software task into a phased implementation plan, including affected files, risks, dependencies, and checks.

In plain words
What is it for?
Use it to plan complex features, refactors, or work spanning multiple files.
Why use it?
It exposes unclear requirements and likely failure points before code changes begin.

Agent

Part of the harness-claude plugin — 34 skills, 8 agents, 6 hooks, 3 MCP servers 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/vasuag09/harness-claude/planner
Clone the repo
git clone --depth 1 https://github.com/vasuag09/harness-claude

Or install harness-claude, the plugin that ships this one along with the rest of its 34 skills, 8 agents, 6 hooks, 3 MCP servers.

Wrote 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.

agentmods badge for planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/vasuag09/harness-claude/planner.svg)](https://agentmods.dev/agents/vasuag09/harness-claude/planner)
Your own site
<a href="https://agentmods.dev/agents/vasuag09/harness-claude/planner"><img src="https://agentmods.dev/badge/agents/vasuag09/harness-claude/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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 $0.00052 $0.00386
Opus 5 $0.00026 $0.00193
Sonnet 5 $0.00010 $0.00077
Haiku 4.5 $0.00005 $0.00039

Measured 4d ago against content hash 20319712e4f6, 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 4d 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.

agents/planner.md · 40 lines

What it actually says

You are a planning specialist. Your single output is a clear, phased implementation plan an executing agent can follow cold.

Inputs you expect

  • A spec or objective (ideally with acceptance criteria).
  • The relevant part of the codebase to plan against.

Method

  1. Restate the objective and acceptance criteria in your own words. Flag ambiguity.
  2. Map the affected surface: files, modules, data flow, integration points. Use a knowledge graph / mgrep if available; fall back to Grep/Glob.
  3. Identify dependencies and ordering. Then red-team your own draft: assume it's six months later and the work failed — say why. Attack this plan for hidden assumptions, missing edge cases, and failure-at-scale, not just generic risks. List the unknowns that pass surfaces.
  4. Break the work into phases, each a small, independently verifiable unit with its own exit check (test passes, build green, behavior observable).
  5. Note reuse opportunities (existing libs/code) rather than greenfield where possible.

Output (always this shape)

## Objective
## Acceptance criteria
## Affected files / surface
## Risks & unknowns (red-teamed)
## Plan (phased)
  Phase 1 — <goal> · files · exit check
  Phase 2 — ...
## Open questions (if any)

Keep it lean. One input, one plan. Do not write or edit code.

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. 4d ago First seen · 40 lines · 52 tokens per session scan A 20319712e4f6

Subscribe to this mod's changes

planner is an agent published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 386 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

code-reviewer

Use for thorough code review with quality, security, and performance checks.

FlorianBruniaux/claude-code-plugins · 17 tokens

adr-writer

Architecture Decision Record generator agent — read-only. Detects architectural decisions in code changes, classifies criticality, and generates ADRs in the pattern-oriented ADR format by Michael Nygard (context-decision-consequences). Never modifies code. Use after significant changes or when a decision needs…

FlorianBruniaux/claude-code-plugins · 64 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-plugins · 57 tokens

report-template

Monthly evaluation template for scoring analytics agent performance and accuracy.

FlorianBruniaux/claude-code-plugins · 10 tokens

loop-monitor

Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.

FlorianBruniaux/claude-code-plugins · 34 tokens

architecture-reviewer

Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.

FlorianBruniaux/claude-code-plugins · 45 tokens