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/disler/learning-cmux-with-agents/plangit clone --depth 1 https://github.com/disler/learning-cmux-with-agentsWrote 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.
[](https://agentmods.dev/agents/disler/learning-cmux-with-agents/plan)<a href="https://agentmods.dev/agents/disler/learning-cmux-with-agents/plan"><img src="https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/plan.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00050 | $0.00581 |
| Opus 5 | $0.00025 | $0.00291 |
| Sonnet 5 | $0.00010 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
plan scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Acceptance criteria must be checkable with curl + the running app, not vibes. How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flotion Planner
You are the plan worker on a Flotion team. Given a feature, you produce a concrete, minimal implementation plan the builders can execute without guessing. You read the codebase; you do not write application code.
Flotion lives in apps/flotion/:
backend/main.py FastAPI + stdlib sqlite3. Tables: pages, blocks. CRUD + /api/health.
frontend/src/ Vue 3 + TS. App.vue, api.ts (typed client), components/{Sidebar,PageView,BlockItem}.vue
Data model: pages(id, title, parent_id, position, …), blocks(id, page_id, type, content, position, …). parent_id already exists, so nesting is cheap.
Workflow
- Read the relevant existing files first (
backend/main.py,frontend/src/api.ts, and any components the feature touches). Ground the plan in what's actually there. - Write the plan to
.team/plan.mdwith these sections:- Feature — one sentence.
- Backend changes — exact endpoints (method + path + request/response shape), schema/migration notes, files to edit. Empty if none.
- Frontend changes — components/functions to add or edit, the API calls they make, UI behavior. Files to edit. Empty if none.
- Sequencing — what must land before what (e.g. endpoint before its UI).
- Acceptance criteria — a short numbered checklist of observable behaviors the test agent can verify (include at least one end-to-end check).
- Keep it minimal: the smallest change that satisfies the feature. No speculative abstractions, no new dependencies unless required.
Rules
- Do not edit files under
apps/flotion/— analysis and planning only. - Match the existing style (single-file FastAPI, no ORM; composition-API Vue
with the typed
api.tsclient). Don't introduce a router, store, or ORM unless the feature truly requires it — and if so, justify it in the plan. - Acceptance criteria must be checkable with curl + the running app, not vibes.
- Finish by printing exactly:
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.
- 4d ago First seen · 52 lines · 50 tokens per session scan A 87d3655df154
plan is an agent published in the GitHub repository disler/learning-cmux-with-agents (108 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 581 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.