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 skills add ai-driven-dev/framework --skill 01-plangit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/skills/ai-driven-dev/framework/01-plan)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/01-plan"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/01-plan/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.
<a href="https://agentmods.dev/skills/ai-driven-dev/framework/01-plan"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/01-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00044 | $0.00472 |
| Opus 5.5 | $0.00018 | $0.00189 |
| Sonnet 5.5 | $0.00009 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
01-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 1mo 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.
What it actually says
Skill: plan
Turn a gathered source into an implementation plan and its phase files. Never writes code.
Actions
| # | Action | Role | Input |
|---|---|---|---|
| 01 | gather |
Collect and restate the source | user request |
| 02 | explore |
Read the codebase for projection, rules, feasibility | gathered source |
| 03 | wireframe |
Sketch a screen at low fidelity, frontend only | source + explore context |
| 04 | plan |
Break into phases, write the plan and phase files | explore output + wireframe |
Run them in order, 01 → 04. The plan is the culmination. Skip 03 when there is no UI.
Before running an action, read its file in actions/, not only the table or assets.
Once the plan and its phase files are written, and only then, run:
echo "aidd:step-end aidd-dev:01-plan"
This is the one thing about a step nothing else can supply. No host reports when a skill's
work finished — a skill call's own result comes back in a tenth of a second, which is the
dispatch, not the completion — so a measurement that never hears this ends the step at the
next pause and credits planning with one turn out of however many it took. The framework
repository documents the run journal this writes into, in aidd_docs/runs/README.md.
References
references/wireframe-conventions.md: how to draw the ASCII wireframe a screen needs.references/plan-status.md: the plan lifecyclestatusvalues and who writes each.
Assets
assets/plan-template.md: theplan.mdscaffold.assets/phase-template.md: the per-phase scaffold.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +12 lines c4fdeb50739a
- 1mo ago Changed · +15 lines · +20 tokens per session f59d7ca07fab
- 1mo ago First seen · 17 lines · 24 tokens per session scan A fc0bdfe637e6
01-plan is a skill published in the GitHub repository ai-driven-dev/framework (518 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 472 once invoked, about $0.0002 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.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
anti-slop-frontend
A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.
anti-slop-image-direction
Opt-in, paid reference images for marketing or new-site work: plan one image per section, confirm count, backend and cost, generate with pi-nano-banana, then distill a written direction brief for the mockup loop. Images are direction, never source. Never for product UI. Triggers: "generate design references", "image…
cadcraft
Headless 2D CAD with CADCraft (DXF/DWG, AutoCAD-style commands, layers, text, dimensions, export to PDF/PNG/SVG, DXF DWG conversion), provisioned on demand by pi-craft. Use for "draw a rectangle and a circle and export a pdf", "convert this dxf to a pdf", "add a layer and a text label to this drawing", "turn this dwg…