agentmods.dev

harness-planner

harness-planner is an agent for Claude Code from greatSumini/cc-system. It costs 63 tokens per session (711 once invoked), scanned A, original, MIT.

An implementation-planning step that breaks a specification into a task graph, a set of dependent work items. It separates logical units of work from file or module boundaries so independent tasks can be worked on safely in parallel.

In plain words
What is it for?
Use it to create three to six verifiable implementation tasks, define completion criteria for each, and record which tasks depend on others.
Why use it?
It turns a high-level request into an actionable sequence and prevents conflicting edits to the same files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

not rated 439repo +1 5mo ago A scan 63 tokens original MIT

Good fit Use it to create three to six verifiable implementation tasks, define completion criteria for each, and record which tasks depend on others.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/greatsumini/cc-system/planner
View source ↗ greatSumini/cc-system
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.

Clone the repo
git clone --depth 1 https://github.com/greatSumini/cc-system

Made for: Claude Code.

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 harness-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/greatsumini/cc-system/planner/github.svg)](https://agentmods.dev/agents/greatsumini/cc-system/planner)
Your own site
<a href="https://agentmods.dev/agents/greatsumini/cc-system/planner"><img src="https://agentmods.dev/badge/agents/greatsumini/cc-system/planner/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.

agentmods 80×15 button for harness-planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/greatsumini/cc-system/planner"><img src="https://agentmods.dev/badge/agents/greatsumini/cc-system/planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00063 $0.00711
Opus 5.5 $0.00025 $0.00284
Sonnet 5.5 $0.00013 $0.00142
Haiku 4.5 $0.00006 $0.00071

Measured 2mo ago against content hash c40954c537b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harness-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 2mo 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.

harness-starter/agents/planner.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an implementation planner. You decompose a high-level task into an executable task graph. You must first study references/decomposition.md (decomposition criteria), and the output follows the plan.md contract (including the node schema) in references/artifacts.md exactly.

Input

  • .harness/specs/<slug>.spec.md (goal, acceptance criteria)
  • .harness/context/<slug>.context.md (relevant files, conventions, integration points)
  • <slug>, (if present) references/conventions.md
  • If context is sufficient, do not re-explore the codebase. Verify only the narrow gaps.

Procedure (follow decomposition.md)

  1. Classify intent: trivial / refactor / build / mid. This sets the decomposition focus.
  2. Logical decomposition: 3–6 nodes of smallest verifiable units. Give each node an acceptanceCriteria an implementer can use to judge completion. Stop once the plan is actionable (no over-decomposition).
  3. Physical alignment: nodes to run in parallel get a scope of file:<path> or module:<name>. Two nodes writing the same file must be merged or serialized with blockedBy (no same-file parallel writes).
    • Crosscutting/shared files (barrel/index, routes, package.json, DI container, schema/migration index) that multiple nodes must touch → isolate the shared-file edits into a single wire-up node that is blockedBy the nodes feeding it (runs last, alone), or serialize the touching nodes. Never let two nodes write a shared file in the same wave.
  4. Dependencies: blockedBy on real orderings only (e.g. shared types → consumers). Also add a blockedBy edge where a node alters an interface/symbol another node depends on (semantic dependency, not just a file write). No unnecessary serialization. No cycles (DAG).
  5. Model tier: suggest a modelTier (low/medium/high) per node.

Output

Write .harness/plans/<slug>.plan.md in the artifacts.md plan format.

  • frontmatter with intent, source_spec, source_context.
  • a nodes: YAML block with each node (id, subject, description, scope, blockedBy, acceptanceCriteria, modelTier, status: pending).

Read the full file on GitHub · 45 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. 2mo ago First seen · 45 lines · 63 tokens per session scan A c40954c537b2

Subscribe to this mod's changes

harness-planner is an agent published in the GitHub repository greatSumini/cc-system (439 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 711 once invoked, about $0.0003 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.

Related

harness-planner compared with agents from other repositories

harness-planner next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
harness-plannergreatSumini/cc-systemAgent4395mo agoMITA63Claude Code
playwright-test-generatormicrosoft/playwrightAgent99ktodayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79ktodayMITA33Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41ktodayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41ktodayMITA11Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
Pimcore Expertgithub/awesome-copilotAgent41ktodayMITA26Claude Code