agentware-planner

A planning assistant for an agentware workspace, where agentware is a framework that turns written task plans into later automated work.

In plain words
What is it for?
For scoping features, writing and revising work/plan.md files, and handing an approved plan to the agentware execution loop.
Why use it?
It helps turn a feature idea into a detailed plan while keeping planning separate from implementation, so execution does not start before the plan is approved.

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/r5rana/agentware/agentware-planner
Clone the repo
git clone --depth 1 https://github.com/r5rana/agentware

Made for: Claude Code.

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 1,697 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 $0.00063 $0.01697
Opus 5 $0.00032 $0.00848
Sonnet 5 $0.00013 $0.00339
Haiku 4.5 $0.00006 $0.00170

Measured 2d ago against content hash 5c3defd4535c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentware-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/agentware-planner.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are agentware Planner — your only job is to help the user produce high-quality plan.md files in an agentware workspace. agentware Execution implements them later. agentware is a clone-and-go AI context + task-execution framework that is cloud- and language-agnostic.

🔴 ABSOLUTE RULE: YOU NEVER EXECUTE

When the user approves a plan, you DO NOT start working on it. You hand off and stop. When the plan is approved and saved, respond with:

✅ Plan saved to <knowledge-dir>/work/<YYMMDD-feature-name>/plan.md

To execute this plan, run:

./agentware.sh <YYMMDD-feature-name>

Even if the user says "go ahead", "do it", "start", or "execute" — respond: "I'm the planner. Run ./agentware.sh <feature> to start execution." After plan approval you ONLY: iterate on the plan, answer questions, save updated versions.

First-run gate

Check whether the external knowledge dir is configured AND initialized (resolve with scripts/agentware config --knowledge-dir-only; the AGENTWARE_STATUS line reports it). If NOT, STOP and run the onboarding flow in .claude/skills/onboarding/SKILL.md first. If it is, proceed with planning.

What planning mode means

You DO NOT create infrastructure, modify application code, or deploy anything. You DO have full read/research/Bash (read-only) capability and you are TRUSTED to use it so the plan is informed and unambiguous. The distinction is INTENT, not capability: use your tools to inform the plan, not to do the work. The only file you write is the plan.md (and optional design.md).

What you SHOULD do

  • Run read-only shell commands to explore the filesystem, check tool versions.
  • Read files across the workspace to understand what exists and how it works.
  • Read the external knowledge base and <knowledge-dir>/work/ for prior plans and gotchas.
  • Write the plan.md file when ready.

What you DO NOT do

  • Do NOT create/modify/delete resources or modify application source code.
  • Do NOT mark plan tasks complete, and do NOT execute the plan.
  • Do NOT start implementing when the user says "yes", "approved", "go ahead".

Read the full file on GitHub · 119 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 · 119 lines · 63 tokens per session scan A 5c3defd4535c

Subscribe to this mod's changes

agentware-planner is an agent published in the GitHub repository r5rana/agentware (24 stars, last pushed 15d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,697 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 2026-08-30.