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 me2resh/apexyard --skill prototype-closegit clone --depth 1 https://github.com/me2resh/apexyardWrote 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/me2resh/apexyard/prototype-close)<a href="https://agentmods.dev/skills/me2resh/apexyard/prototype-close"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/prototype-close/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/me2resh/apexyard/prototype-close"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/prototype-close.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 | $0.00045 | $0.02682 |
| Opus 5.5 | $0.00018 | $0.01073 |
| Sonnet 5.5 | $0.00009 | $0.00536 |
| Haiku 4.5 | $0.00005 | $0.00268 |
Grade A, and why
prototype-close 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 22d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing: read docs/skills/shared/writing-rule.md before you write a durable artifact.
/prototype-close — Close a Prototype via the Disposition Gate
The disposition gate prevents the worst-of-both case: a prototype that "looked great in the demo" but never decides what to do with it, leaving a throwaway mockup that quietly gets promoted into production. Every prototype must close with one of two paths:
- PROMOTE — the direction was chosen; file a fresh
[Feature]ticket so the real work goes through the full production SDLC. The prototype artifact is NOT lifted into production — the new feature re-implements based on the chosen direction. - DISCARD — the direction was rejected (or "not now"); write a memo at
docs/prototype-memos/<slug>.mdso future-us doesn't re-explore the same ground.
This is the UX/demo sibling of /spike-close (technical exploration). Same gate, same two paths, different artifact directory (docs/prototype-memos/ vs docs/spike-memos/).
Path resolution
Read the registry path via portfolio_registry, the per-project docs dir via portfolio_projects_dir, and the ideas backlog via portfolio_ideas_backlog — all from .claude/hooks/_lib-portfolio-paths.sh. Source the helper at the top of any bash block that touches those paths:
source "$(git rev-parse --show-toplevel)/.claude/hooks/_lib-read-config.sh"
source "$(git rev-parse --show-toplevel)/.claude/hooks/_lib-portfolio-paths.sh"
registry=$(portfolio_registry)
Defaults match today's single-fork layout. See docs/multi-project.md.
Usage
/prototype-close --promote 142
/prototype-close --discard 142
/prototype-close --promote # uses the active-ticket marker
/prototype-close --discard
Process
1. Resolve the prototype ticket
Two paths:
- If
$ARGUMENTSincludes a number (e.g.--promote 142or--discard owner/repo#142), use that. - Otherwise read the active-ticket marker of the working tree you are in (see
/start-ticket"Read the active ticket") and use the ticket recorded there. If no marker resolves, ask:
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.
- 22d ago Changed · -2 lines 85b8c52abf69
- 1mo ago Changed · +4 lines a5bba8ede623
- 2mo ago First seen · 274 lines · 45 tokens per session scan A 767f9e999cc4
prototype-close is a skill published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 2,682 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.
prototype-close compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prototype-closeme2resh/apexyard | Skill | 542 | yesterday | MIT | A | 45 | Claude Code |
| aesthetic-instrumentavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 106 | Claude Code |
| committed-aestheticavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 94 | Claude Code |
| anydesignavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 214 | Claude Code |
| swiftui-design-consultationParetofilm/superpowers-gstack | Skill | 3 | 2d ago | none | A | 50 | Claude Code |
| apple-native-reviewParetofilm/superpowers-gstack | Skill | 3 | 2d ago | none | A | 59 | Claude Code |
| swiftui-view-gateParetofilm/superpowers-gstack | Skill | 3 | 2d ago | none | A | 39 | Claude Code |