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-convergencegit 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)<a href="https://agentmods.dev/skills/markasir/design-plan-skill/design-plan-convergence"><img src="https://agentmods.dev/badge/skills/markasir/design-plan-skill/design-plan-convergence.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 5.1 | $0.00084 | $0.03055 |
| Opus 5 | $0.00042 | $0.01528 |
| Sonnet 5 | $0.00017 | $0.00611 |
| Haiku 4.5 | $0.00008 | $0.00305 |
Grade A, and why
design-plan-convergence 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 7d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design and Plan Convergence Audit
Core contract
Audit one current readiness gate from current evidence. Keep the audit read-only. Treat old reports and modifier summaries as claims, never as facts.
- Read applicable organization, project, methodology, repository, and artifact-format rules.
- Freeze the charter, gate, artifact set, Non-Goals, decisions, accepted risks, evidence boundary, and snapshot.
- Use the smallest evidence set that proves or disproves the gate, including complete affected decision chains and siblings.
- Do not edit artifacts, implement future work, run release verification, or broaden the charter.
- Route only
BLOCKERandREQUIREDfindings to remediation.
Choose one audit mode:
- Audit: inspect the current artifact without relying on an earlier verdict.
- Re-audit: verify claimed repairs on the current snapshot.
- Convergence: detect recurrence, drift, and repair-created mechanisms.
Select the gate and risk profile
Use the explicit gate, otherwise infer it from the primary artifact:
| Gate | Current responsibility |
|---|---|
DESIGN READY |
OpenSpec or equivalent design contracts, decisions, compatibility, risks, and recovery principles are sufficient to write a plan. |
PLAN READY |
An existing implementation plan is aligned, ordered, feasible, and mechanically verifiable. |
IMPLEMENTATION READY |
Route only when the user explicitly asks to verify completed implementation or invokes the repository implementation-verification workflow. |
RELEASE READY |
Route only on an explicit release-readiness request after implementation evidence and a release candidate or target environment exist. |
Do not automatically advance from document convergence to implementation or release.
A missing plan at DESIGN is NEXT STAGE NOT STARTED, not a blocker.
Use AUTO unless the user selects LEAN or ASSURANCE:
LEAN: cover the main flow, approved boundaries, credible single failures, and mandatory safety/data protections.AUTO: apply LEAN globally and a localASSURANCE SLICEonly to security/trust boundaries, money/quota, irreversible data changes, public compatibility, concurrency/idempotency/state machines, or production activation/rollback.ASSURANCE: deepen evidence for the selected gate; never change the gate or authorize implementation.
What ships with it
7 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.
- 7d ago First seen · 257 lines · 84 tokens per session scan A 5cd34abf27d5
design-plan-convergence is a skill published in the GitHub repository MarkAsir/design-plan-skill (1 stars, last pushed 8d ago), licensed MIT. It adds 84 tokens to every session and 3,055 once invoked, about $0.0004 per session on Opus 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…
fde
Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…
kubernetes-skill
Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and…
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.
img2mo-learn
Learn reusable 2D motion-generation knowledge from user-specified action resources with /img2mo-learn . Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style…
img2mo-std
Standardize a 2D animation baseline image with /img2mo-std xxx.png/pos. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/attack/idle frames…