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/work0r-ai/agent-kit/agents-mdgit clone --depth 1 https://github.com/work0r-ai/agent-kitWhat 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 | $0.01757 | $0.01757 |
| Opus 5 | $0.00879 | $0.00879 |
| Sonnet 5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
agent-kit 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 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository packages the WorkorAI talent marketplace Agent Skill for public distribution. The single workorai skill covers both candidate (9 tools: job search, job detail, applications, apply, invitation accept/decline, withdraw, saved jobs) and employer (18 tools: job lifecycle, candidate discovery, invitations, applicants review) workflows on the WorkorAI MCP server.
Structure
skills/workorai/is the canonical skill folder for GitHub and skill registries.skills/workorai/SKILL.mdis the required Agent Skills entry point.skills/workorai/agents/openai.yamlis UI metadata for Codex/OpenAI-style skill surfaces.skills/workorai/references/contains progressively loaded domain references.skills/workorai/scripts/credential-store.mjsstores WorkorAI MCP keys after explicit user consent.skills/workorai/LICENSE.txtis the per-skill license for registries that inspect skill folders directly.bin/workorai-agent.mjsinstalls the skill and writes MCP config for supported local agent clients.registry/contains human-facing submission notes for external skill hubs.- Supported explicit install targets include Codex, Claude Code, OpenCode, Cursor, OpenClaw-compatible clients, Qwen Code, Antigravity, Deep Code, and generic
.agentshosts.
Maintenance Rules
- Keep
skills/workoraias the source of truth. Do not reintroduce a secondtemplates/copy. - If the skill behavior changes, update
README.md,CHANGELOG.md, and relevantregistry/*.mdfiles. - If the CLI install paths change, update
README.mdand runnpm run validate. - Never commit real WorkorAI MCP keys. Examples must use redacted
wai_[REDACTED]values. - Preserve compatibility with Node.js 18+ and avoid runtime dependencies unless they are clearly necessary.
Validation
Run:
npm run validate
npm run smoke
npm pack --dry-run
The smoke test installs into a temporary directory only.
ClawMem — Semantic Code Memory
⚠️ Not indexed yet. Add to
~/.config/clawmem/index.ymlto enable.
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 · 149 lines · 1,757 tokens per session scan A a7466db7723a
agent-kit AGENTS.md is an instructions file published in the GitHub repository work0r-ai/agent-kit (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,757 tokens to every session, about $0.0088 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 instructions, from other repositories
mcp-steroid CLAUDE.md
Instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.
nopua AGENTS.md
Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.
supergraph AGENTS.md
Instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
skills CLAUDE.md
Instructions for mixedbread-ai/skills, covering mixedbread skills, repository structure, conventions, adding a new skill and testing a skill.
video-podcast-maker AGENTS.md
AGENTS.md instructions for Agents365-ai/video-podcast-maker, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.