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 igloude/ds-skills --skill ds-plangit clone --depth 1 https://github.com/igloude/ds-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/igloude/ds-skills/ds-plan)<a href="https://agentmods.dev/skills/igloude/ds-skills/ds-plan"><img src="https://agentmods.dev/badge/skills/igloude/ds-skills/ds-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/igloude/ds-skills/ds-plan"><img src="https://agentmods.dev/badge/skills/igloude/ds-skills/ds-plan.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 | $0.00029 | $0.02245 |
| Opus 5 | $0.00015 | $0.01123 |
| Sonnet 5 | $0.00006 | $0.00449 |
| Haiku 4.5 | $0.00003 | $0.00225 |
Grade A, and why
ds-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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds-plan
Decide what gets built, from what, before anything is built. Every violation a gate catches was really a decision made seconds earlier, when someone — increasingly a generating agent — picked a component and guessed at its props. This skill moves that decision upstream, makes it with the actual API in hand, and writes it down. The byproduct is free: the extensions and gaps a feature exposes are exactly the design system's next backlog, discovered by demand instead of by committee.
The output is falsifiable, which is the point: run /ds-drift on the branch that implements this map, and every element you marked Covered should pass. If it doesn't, either the map was wrong or the generator ignored it — both worth knowing.
This skill is report-only and every output must survive a cold read — both terms, the family rules they summarize, and the plans/ directory conventions are defined in ../ds-drift/references/conventions.md. Read it now; it is short and load-bearing.
Skill rules
- Family rule 5 is this skill's center of gravity: every Covered and Composable classification cites the manifest inventory row or the component's actual types at
file:line, and names every prop it claims. Unverified means not Covered — classify it down the ladder and say why. - A Don't-build verdict quotes its policy source — the manifest's policy zone, a documented guideline, or a deprecation record. No citation, no verdict: classify the element on the ladder and record the concern as advisory. Pushing back on a designer is authority you spend, not authority you assume.
- Coverage maps carry a
-map-slug (plans/NNN-map-<slug>.md) so maps, reviews, and plans read apart in the shared directory.
Done means
A run is done when: the map file exists and survives a cold read; every inventoried element appears exactly once, in exactly one bucket, marked drawn or implied; every Covered and Composable row cites file:line in real types; every Extension and Net-new item names what it blocks and an interim strategy; and "Not classified" and the confidence line are filled in — even when the answers are "none" and "HIGH". Phase 6 checks exactly this before you finish.
What ships with it
3 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.
- 9d ago First seen · 92 lines · 29 tokens per session scan A c818a486eb32
ds-plan is a skill published in the GitHub repository igloude/ds-skills (8 stars, last pushed 20d ago), licensed MIT. It adds 29 tokens to every session and 2,245 once invoked, about $0.0001 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
system-pitch
Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…
stakeholder-brief
Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…
token-audit
Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…
accessibility-per-component
Run an accessibility audit on a specific design system component. Trigger when someone says: accessibility check, a11y audit, WCAG compliance, is this accessible, check accessibility, does this meet WCAG, screen reader support, keyboard navigation check, or anything about auditing the accessibility of a specific…
ai-component-description
Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…
context-engine-builder
Generate a context engine — seven structured blueprint files (UX, UI, content, accessibility, ethical, technical, business intelligence) that encode everything an AI agent needs to work with a design system. This produces YAML infrastructure in .ai/context-engine/, NOT a health score or quality assessment. Trigger…