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 instructions/workos/skills/agents-mdgit clone --depth 1 https://github.com/workos/skillsWhat 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 | $0.01631 | $0.01631 |
| Opus 5 | $0.00816 | $0.00816 |
| Sonnet 5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
skills AGENTS.md 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- skills CLAUDE.md — 94% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@workos/skills
Codex plugin providing WorkOS integration skills (AuthKit, SSO, Directory Sync, RBAC, FGA, etc.).
Commands
# Testing & formatting
pnpm test # run tests (vitest)
pnpm format # oxfmt
pnpm lint # oxlint
# Evals
pnpm eval -- --dry-run # verify cases load (no API key needed)
pnpm eval -- --no-cache # full run, skip cache
pnpm eval -- --no-cache --product=sso # run specific product
pnpm eval -- --no-cache --case=sso-node-basic # run single case
pnpm eval -- --no-cache --fail-on-regression # full run with gates
pnpm eval -- --no-cache --samples=2 # multi-sample for variance measurement
pnpm eval -- --no-cache --samples=2 --save-all-samples # + persist all sample outputs
# Eval tooling
pnpm eval:diff -- --case=sso-node-basic # side-by-side transcript diff with signal highlighting
pnpm eval:label -- --case=X --ship=yes --who=nick --reason="..." # add human judgment
pnpm eval:calibrate # compare scorer vs human labels
Project Structure
.agents/plugins/marketplace.json— Codex marketplace catalog (source:./plugins/workos).cursor-plugin/marketplace.json— Cursor marketplace catalog (mirrors Claude catalog)plugins/workos/— installable plugin (only this gets cached).codex-plugin/plugin.json— Codex plugin manifest.cursor-plugin/plugin.json— Cursor plugin manifest (mirrors Claude manifest; versions synced by release-please)skills/— skill directories, each withSKILL.md- Hand-crafted AuthKit skills:
workos-authkit-base,workos-authkit-nextjs,workos-authkit-react,workos-authkit-react-router,workos-authkit-tanstack-start,workos-authkit-vanilla-js,workos-widgets - Router:
workos/SKILL.md— routes user requests to the right topic file or AuthKit skill - Topic files:
workos/references/*.md— lean files with doc URLs + gotchas + optional endpoint tables
- Hand-crafted AuthKit skills:
scripts/— eval framework (not cached with plugin)tests/—*.spec.tsfiles using vitest
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.
- 2d ago First seen · 130 lines · 1,631 tokens per session scan A 1e043706db4d
skills AGENTS.md is an instructions file published in the GitHub repository workos/skills (45 stars, last pushed 26d ago), licensed MIT. It adds 1,631 tokens to every session, about $0.0082 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 instructions, from other repositories
horizun-pbi-mcp AGENTS.md
AGENTS.md instructions for HorizunGroup/horizun-pbi-mcp, covering repository rules for agents, 1. before touching anything, 2. the mcp contract is untouchable, 3. invariants no phase can break and 4. real data: never enters git.
powerbi-mcp AGENTS.md
Instructions for sulaiman013/powerbi-mcp, covering power bi mcp server - agent guide, what this server does, golden rules, recommended workflows and prompts (guided workflows).
pbi-context CLAUDE.md
Instructions for Osc2405/pbi-context, covering estado actual (actualizado 2026-07-15), actualización 2026-08-03 — rename pbi-docs → pbi-context, 0. contexto del proyecto (no re-investigar, ya validado), 1. feature obligatoria: soporte .pbip / tmdl and por qué es obligatoria (contexto de mercado, no opinable).
powerbi-mcp CLAUDE.md
Instructions for sulaiman013/powerbi-mcp, covering claude.md and developer notes.
powerbi-agent CLAUDE.md
Claude Code instructions for ducnguyen221/powerbi-agent, a project described as: MCP server + skills for AI agents to work directly with Power BI — DAX query with data-safety policy, PBIR report templates, end-to-end analysis pipeline (Claude Code / Codex / Antigravity).
powerbi-agent GEMINI.md
Gemini CLI instructions for ducnguyen221/powerbi-agent, a project described as: MCP server + skills for AI agents to work directly with Power BI — DAX query with data-safety policy, PBIR report templates, end-to-end analysis pipeline (Claude Code / Codex / Antigravity).