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 agentmods add skills/workstream-labs/workstreams/accessibilitynpx skills add workstream-labs/workstreams --skill accessibilitygit clone --depth 1 https://github.com/workstream-labs/workstreamsWhat 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 | $0.00054 | $0.03503 |
| Opus 5 | $0.00027 | $0.01751 |
| Sonnet 5 | $0.00011 | $0.00701 |
| Haiku 4.5 | $0.00005 | $0.00350 |
Grade A, and why
accessibility 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 304 lines · 54 tokens per session scan A dbd8bb67ada4
accessibility is a skill published in the GitHub repository workstream-labs/workstreams (77 stars, last pushed 4mo ago), with no licence file. It adds 54 tokens to every session and 3,503 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
adversarial-review
Multi-role adversarial code review (platform skill). Agent loads this skill and runs the co-located runner (find → refute → sandbox repro); humans only state intent (审一下 / 对抗审查). Works for OpenClaw Main and host TUI agents via user-level skill links. Use when user asks for adversarial review, acceptance recommends…
dev-task
Allowlisted development (wezdeck (+ optional team roots in local config)) under OpenClaw: wezdeck defaults to primary master; claw worktrees when parallel/isolation needed; 团队仓 still prefers claw-; human/Claw rails (H1/H2, C1/C2/C3), ACP access layer.
task-ledger
Ledger development tasks to Feishu Base via dev-task-ledger.sh. Write roots from /.openclaw/tasks-allowlist.json (per agent). Use on accept/confirm/close of coding/ops work; not for pure Q&A.
brainstorm
Multi-persona divergent→convergent brainstorm (platform skill). Agent loads this skill and runs the co-located runner (diverge → challenge → converge); humans only state intent (头脑风暴 / 帮我发散一下 / brainstorm / 想点子). Sibling of adversarial-review; reuses its provider layer. Use when the user wants ideas / options /…
yuns-engineer
Engineer judgment for concrete problems: evidence → options → decision → verify → mine transferable practice. Routes real capabilities when needed and distills design decisions + personal preferences. Load for adjudication, multi-option recommendations, or end-of-task experience capture. Not idea divergence…
chrome-devtools
Drive the machine Chrome debug browser via OpenClaw-managed MCP (chrome-devtools). Use for page navigation, snapshots, screenshots, clicks, forms, console/network inspection — not for host shell risk.