agentware-plan

agentware-plan is a command for Claude Code from r5rana/agentware. It costs 0 tokens per session (476 once invoked), scanned A, original, Apache-2.0.

A command for creating a written feature plan in an Agentware workspace. It checks project instructions and current work before recording the plan.

In plain words
What is it for?
Use it to gather requirements, classify work as infrastructure, code, configuration, or knowledge, and create the project’s planned work folder.
Why use it?
It gives a feature a shared plan, design notes, tasks, and acceptance checks before implementation begins.

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

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 agentware-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/r5rana/agentware/agentware-plan.svg)](https://agentmods.dev/commands/r5rana/agentware/agentware-plan)
Your own site
<a href="https://agentmods.dev/commands/r5rana/agentware/agentware-plan"><img src="https://agentmods.dev/badge/commands/r5rana/agentware/agentware-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 476 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 $0.00000 $0.00476
Opus 5 $0.00000 $0.00238
Sonnet 5 $0.00000 $0.00095
Haiku 4.5 $0.00000 $0.00048

Measured 3d ago against content hash 49788e63bf89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentware-plan 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 3d 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/commands/agentware-plan.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.

@agentware-plan

Create a new feature plan for the loop to execute in this agentware workspace.

Instructions

  1. Read docs/loop.md to understand how to create plan and design documents.
  2. Read AGENTS.md for the project's execution methodology.
  3. Read the knowledge base MAIN.md (resolve its dir via scripts/agentware config --knowledge-dir-only) for current active work.
  4. Ask the user for the feature requirements (3–5 targeted questions max).
  5. Determine which task types are involved:
    • infra — environment / resource provisioning using the project's own tooling (no assumed cloud verbs).
    • code — code changes in this workspace or a sibling workspace.
    • config — configuration changes deployed to running services.
    • knowledge — knowledge-base updates (entries, index.json, MAIN.md).
  6. Create a docs directory: <knowledge-dir>/work/<YYMMDD-feature-name>/.
  7. Write plan.md with phases, tasks, and acceptance criteria following the format in docs/loop.md.
  8. Optionally create design.md for complex features.
  9. Tell the user which folder you created the files in.
  10. Suggest the user run ./agentware.sh <feature-name> to execute the plan, or re-run the planner to iterate.

Task scoping guidelines

  • Each task should be one logical unit of work.
  • Infrastructure tasks: one resource per task.
  • Knowledge-base tasks: group related updates (e.g. "Create project entry + update index.json").
  • Cross-workspace code tasks: one coherent change per task.
  • Every task MUST have verifiable acceptance criteria expressed in the project's own commands.

Conventions for plan content

  • Naming: {project}-{resource}-v{version} unless the project documents its own.
  • Relative paths inside repo files; resolve the external knowledge dir at runtime.
  • Verification: each task lists a concrete check (file exists, test passes, command output, etc.).
  • Always include a knowledge-base-update task in the final phase.
  • Set the promise tag at the top of the plan: <promise>YYMMDD_FEATURE_NAME_COMPLETE</promise>.

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. 3d ago First seen · 45 lines · 0 tokens per session scan A 49788e63bf89

Subscribe to this mod's changes

agentware-plan is a command published in the GitHub repository r5rana/agentware (24 stars, last pushed 16d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 476 tokens. 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.