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.
npx agentmods add agents/r5rana/agentware/agentware-plannergit clone --depth 1 https://github.com/r5rana/agentwareWhat 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.
| Model | Per session | Once 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 |
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.
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.mdTo 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.mdfile 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".
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.
- 2d ago First seen · 119 lines · 63 tokens per session scan A 5c3defd4535c
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.