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-driftgit 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-drift)<a href="https://agentmods.dev/skills/igloude/ds-skills/ds-drift"><img src="https://agentmods.dev/badge/skills/igloude/ds-skills/ds-drift/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-drift"><img src="https://agentmods.dev/badge/skills/igloude/ds-skills/ds-drift.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 | $0.00031 | $0.02843 |
| Opus 5 | $0.00015 | $0.01422 |
| Sonnet 5 | $0.00006 | $0.00569 |
| Haiku 4.5 | $0.00003 | $0.00284 |
Grade A, and why
ds-drift 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds-drift
Judge whether work — increasingly, work produced by other models — conforms to this repo's design system, render a verdict a team can trust, and specify every required change precisely enough that the generating agent or a cheaper executor applies it without you. The review is the product. A noisy gate is an ignored gate, so precision outranks recall everywhere in this skill.
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 references/conventions.md. Read it now; it is short and load-bearing.
Skill rules
- Report the gap the toolchain can't see. If tsc, eslint, or an existing lint rule would flag it, it is not a finding — it is noise that erodes the gate's authority.
- Severity comes from policy, not per-run invention. Use the manifest's severity map (fall back to the playbook defaults) and honor its waiver ledger. Consistency between runs is what makes the verdict meaningful.
- Review files carry a
-review-slug (plans/NNN-review-<slug>.md) so reviews and plans read apart in the shared directory.
Done means
A gate/batch run is done when: the review file exists and survives a cold read; every blocking finding carries a verify command with an expected result; every finding is tagged introduced or pre-existing; every element of the Phase 2 scope was audited or named under "Not audited"; and the verdict recomputes mechanically from the stated counts and policy. Phase 5 checks exactly this before you finish.
Workflow
Phase 1 — Recon (always)
Manifest first. The conformance manifest is both the rulebook and your recon cache. Locate it in this order: a --manifest <path> argument → ds/MANIFEST.md + ds/tokens.json in the repo root → node_modules/<ds-package>/ds/ (design systems that publish their manifest; find packages by globbing node_modules/{*,@*/*}/ds/MANIFEST.md). Manifests are per-package: multiple hits are a monorepo consuming several DS packages, not an error — load each, judge every component and token against the manifest of the package that owns it (the package it is imported from, or whose token namespace it matches), and report per package. A component name claimed by two manifests is a conflict to report, never a guess. --manifest restricts a run to one. Read the severity policy, waiver ledger, exclusions table, component inventory, and synonym map — excluded paths are skipped entirely and listed under the review's "Not audited" line.
What ships with it
6 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 · 101 lines · 31 tokens per session scan A 5731152d9be5
ds-drift is a skill published in the GitHub repository igloude/ds-skills (8 stars, last pushed 20d ago), licensed MIT. It adds 31 tokens to every session and 2,843 once invoked, about $0.0002 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
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
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…