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 MarkAsir/design-plan-skill --skill design-plan-convergence-loopgit clone --depth 1 https://github.com/MarkAsir/design-plan-skillWrote 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/markasir/design-plan-skill/design-plan-convergence-loop)<a href="https://agentmods.dev/skills/markasir/design-plan-skill/design-plan-convergence-loop"><img src="https://agentmods.dev/badge/skills/markasir/design-plan-skill/design-plan-convergence-loop/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/markasir/design-plan-skill/design-plan-convergence-loop"><img src="https://agentmods.dev/badge/skills/markasir/design-plan-skill/design-plan-convergence-loop.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00096 | $0.03091 |
| Opus 5.5 | $0.00038 | $0.01236 |
| Sonnet 5.5 | $0.00019 | $0.00618 |
| Haiku 4.5 | $0.00010 | $0.00309 |
Grade A, and why
design-plan-convergence-loop 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.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design and Plan Convergence Loop
Contract
Drive one artifact generation to one document readiness gate. Treat OpenSpec and Superpowers as optional format adapters, not prerequisites:
- use
design-plan-convergencefor audit and independent closure; - use
design-plan-remediationfor every authorized mutation; - never let the modifier close its own findings or grant READY;
- never modify implementation, external systems, frozen decisions, or paths outside the allowlist;
- an audit-only request runs one audit and stops;
- default completion is
DESIGN READYorPLAN READY, not implementation or release.
Read references/modes-and-gates.md to select the artifact lifecycle and references/orchestration-and-state.md to manage snapshots, trend, context, and termination. Read references/runtime-budget-and-cleanup.md before estimating work, persisting a multi-cycle run, pausing, resuming, or cleaning runtime state.
Freeze the run
Record:
mode, target gate, and LEAN/AUTO/ASSURANCE profile
artifact generation and editable path set
read-only evidence boundary
charter, scope, Non-Goals, must-not-change behavior
frozen decisions, accepted risks, unresolved decisions
applicable rules and artifact profile
Acceptance Kernel, DIRECT contract roots, and approved boundary semantics
applicable defect classes, coverage obligations, and global invariants
completion criteria and current snapshot
complexity class, soft time budget, and mandatory coverage partitions
The Acceptance Kernel is the frozen charter, scope, Non-Goals, decisions, DIRECT roots, boundary semantics, risk profile, and applicable rules that define the current review space. Start a new artifact generation only when this kernel, the artifact boundary, or a key mechanism changes. A root-preserving repair or a justified DERIVED contract does not start a new generation.
Gate priority:
What ships with it
4 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 First seen · 283 lines · 96 tokens per session scan A f3d135107180
design-plan-convergence-loop is a skill published in the GitHub repository MarkAsir/design-plan-skill (1 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 3,091 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
ideagram
Turn a concept, feature description, blog post, or pitch into a single beautiful, on-brand illustration by matching it to a real unDraw illustration in a local library and recoloring it to the brand accent — genuine illustrator quality, not an AI-drawn approximation. Use whenever the user asks to "make an…
image-to-psd
A skill that reconstructs images as editable, layered Photoshop files. It separates the repaired background, visual components, and text into layers instead of leaving the page as one flat image.
compose-ui-builder
Open and edit checked-in .uid designs, compare real renders against references, and implement them in application code. Author and edit a Compose UI design over MCP against a compose-preview serve deployment — create a screen or a Wear widget, insert and edit nodes, and export the Kotlin, PNG or SVG. Also use when no…
frontend-patterns
CSS design system principles -- token usage, semantic layering, mobile-first, component isolation.
design-parity-review
Prove a Compose UI pull request matches its intended design by diffing the rendered code (candidate) against a Figma / Stitch / Claude Design reference and posting a parity verdict. Use when asked to check a PR against a design, wire up a design-parity bot, set up the committed reference cache so runs make zero Figma…