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 Owl-Listener/inclusive-design-skills --skill reviewgit clone --depth 1 https://github.com/Owl-Listener/inclusive-design-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/owl-listener/inclusive-design-skills/review)<a href="https://agentmods.dev/skills/owl-listener/inclusive-design-skills/review"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/review/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/owl-listener/inclusive-design-skills/review"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/review.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 | $0.00058 | $0.00525 |
| Opus 5.5 | $0.00023 | $0.00210 |
| Sonnet 5.5 | $0.00012 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
review 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 2mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Accessibility Decisions
Surface the accessibility decisions that were made — deliberately or by default — in an existing feature, and document them before they get lost.
Process
Step 1: Identify Implicit Decisions
Walk through the feature and list every design choice that affects accessibility, even if nobody explicitly decided it:
- How is keyboard navigation handled?
- What happens with screen readers?
- What colour and contrast choices were made?
- How are errors communicated?
- What motion and animation exists?
- What user preferences are respected?
Many of these were never consciously decided — they were inherited from a framework, copied from another feature, or left at defaults. Those are still decisions. Document them.
Step 2: Assess Each Decision
For each identified decision, determine:
- Was this intentional or accidental?
- Does it meet current accessibility standards?
- Who does it serve well? Who does it exclude?
- Is there evidence behind it or was it arbitrary?
Step 3: Check for Undocumented Tradeoffs
Using tradeoff-analysis, identify decisions where accessibility was traded for something else:
- Speed: "we didn't have time to make this keyboard accessible"
- Complexity: "the accessible version was too hard to build"
- Design: "the accessible version didn't look right"
- Ignorance: "we didn't know this was an issue"
Document each with its current impact on users.
Step 4: Map Current Compliance
Using compliance-mapping, assess the feature's current state against WCAG 2.2 Level AA. Identify conformance gaps.
Step 5: Catalogue Debt
Using accessibility-debt-tracking, create a debt record for every known issue discovered in this review.
Output
Deliver a decision review report:
- Decision inventory — every accessibility-affecting decision found, marked as intentional or accidental
- Undocumented tradeoffs — decisions where accessibility was sacrificed, with current user impact
- Compliance gaps — WCAG criteria not currently met
- Debt register — known issues with severity, owner, and recommended timeline
- Recommendations — which decisions should be revisited first
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.
- 2mo ago First seen · 65 lines · 58 tokens per session scan A 947c7a52276c
review is a skill published in the GitHub repository Owl-Listener/inclusive-design-skills (108 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 525 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 2026-08-30.
review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reviewOwl-Listener/inclusive-design-skills | Skill | 108 | 5mo ago | MIT | A | 58 | Claude Code |
| accessibility-compliance-accessibility-auditsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 38 | Claude Code |
| ada-plan-view-accessibilitybenchflow-ai/skillsbench | Skill | 1.9k | 3d ago | Apache-2.0 | A | 41 | Claude Code, Codex |
| counselaimeos/pagible | Skill | 602 | 2d ago | MIT | A | 34 | Claude Code, Codex |
| linkfox-sif-compliance-detectionlinkfox-ai/linkfox-skills | Skill | 119 | 9d ago | MIT | A | 91 | Claude Code, Codex |
| auditing-wcagmasuP9/a11y-specialist-skills | Skill | 61 | yesterday | MIT | A | 49 | Claude Code, Codex |
| a11y-ops0xDarkMatter/claude-mods | Skill | 79 | 7d ago | MIT | A | 131 | Claude Code |