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 richfrem/agent-plugins-skills --skill subagent-driven-prototypinggit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/subagent-driven-prototyping)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/subagent-driven-prototyping"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/subagent-driven-prototyping/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/richfrem/agent-plugins-skills/subagent-driven-prototyping"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/subagent-driven-prototyping.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 | $0.00039 | $0.00485 |
| Opus 5.5 | $0.00016 | $0.00194 |
| Sonnet 5.5 | $0.00008 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
subagent-driven-prototyping 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 17d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Prototyping (subagent-driven-prototyping)
Builds prototypes component by component, self-reviewing each against the Discovery Plan before advancing.
Contents
Critical Constraints
- Only advance to the next component when the current component self-review passes and status is
COMPLETE. - Build in isolated worktrees or dedicated prototype directories (
exploration/prototype/). - Never skip plan verification gates between component builds.
Quick start
- Verify presence of approved Discovery Plan and layout direction documents.
- Decompose build into 3–6 manageable parts (e.g. navigation, controls, data view).
- Execute iterative build loop: assemble, review, mark
COMPLETE, and link inindex.html.
Workflow
- Pre-flight: Confirm approved Discovery Plan in
exploration/discovery-plans/and layout inexploration/captures/. - Decomposition: Break the prototype scope into 3–6 modular components.
- Build Loop: Implement each component incrementally matching session mode (greenfield, brownfield, or plugin).
- Self-Review: Compare implementation against Discovery Plan acceptance criteria.
- Assembly: Link finished components into
exploration/prototype/index.htmland produce a completion handoff block.
Verification
- Confirm all defined components compile or render correctly in
exploration/prototype/. - Validate test execution or behavioral assertions for critical logic.
- Verify status for every component in the task ledger is marked
COMPLETE.
References
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.
- 17d ago Changed · -182 lines · -35 tokens per session b67723228dcf
- 1mo ago Changed · -17 lines d9d104b702f0
- 1mo ago First seen · 244 lines · 74 tokens per session scan A e8524ed96eef
subagent-driven-prototyping is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 485 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 2026-09-03.
Other skills, from other repositories
drag-pane
Drag-and-drop pane resizing implementation for two-pane plugin layouts. Covers mouse event handling via the internal/mouse package, hit region registration, drag delta calculation, width clamping, state persistence, and pane layout management. Use when working on pane resizing, drag interactions, layout management, or…
product-ui
Use this skill when UI design and UI implementation should happen together. It turns product context into usable frontend screens, components, layout decisions, design-system choices, accessibility rules, and visual polish.
release
Cut and publish a full stable NAC release after main, release-PR, and publication CI pass. Use when a maintainer asks for a stable version bump, tag, or GitHub Release. Never use for release candidates; NAC RC releases are automated.
ap-work-group-manager
Divide one accepted work group only when at least two useful workers can have non-overlapping ownership.
ap-arbiter
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-implementer
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.