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/usetemi/skills/agents-mdgit clone --depth 1 https://github.com/usetemi/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/instructions/usetemi/skills/agents-md)<a href="https://agentmods.dev/instructions/usetemi/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/usetemi/skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.00563 | $0.00563 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Repository
usetemi/skills publishes Temi agent skills for coding agents and tools that
support the Agent Skills spec. Keep this file focused on instructions agents need
while changing the repo; keep public install, catalog, and distribution copy in
README.md.
Orientation
- Each skill is self-contained under
skills/<name>/.SKILL.mdis the required entry point; deeper references should live inside the skill and be loaded only when the task calls for them. README.mdis the canonical public catalog and install guide. Update it when a skill is added, removed, renamed, or its public description changes.- Plugin and marketplace metadata lives under
.claude-plugin/,.codex-plugin/, and.agents/plugins/. Touch those files only for registration or metadata changes. template/renders shared Python modules for the google-* CLI skills. Readtemplate/AGENTS.mdbefore editing the Copier template or any file generated from it.
Skill Changes
- When adding a new skill, create
skills/<name>/SKILL.mdand keep the skill directory self-contained. - Register new skills in
.claude-plugin/marketplace.jsonand add a row to theREADME.mdskill table. - Codex discovers skills from
./skills/via.codex-plugin/plugin.json, so new skills do not need per-skill Codex registration unless root plugin metadata changes. - Do not document capabilities that are not implemented in the skill.
Copier-Rendered Google Skills
The google-* Python CLI skills share modules rendered from template/. If you
change a template or a rendered shared module, re-render each affected consuming
skill from that skill's directory:
copier copy --data-file .copier-answers.yml --defaults --trust --overwrite ../../template .
Commit the template change and regenerated outputs together. The
copier-drift.yml workflow runs the same copier copy --overwrite flow and fails
if rendered files drift.
Validation
- For Python CLI skills, run:
uv run --project skills/<skill> ruff check . uv run --project skills/<skill> ty check - After editing
template/**, run the Copier re-render command for each affected skill with a.copier-answers.ymlfile and confirm the diff contains only intended changes. - For docs-only edits, re-read the changed guidance and check for duplicated README content, stale file indexes, or command drift.
- Before finishing, run
git diff --check.
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.
- 4d ago First seen · 60 lines · 563 tokens per session scan A 6436f78ec943
skills AGENTS.md is an instructions file published in the GitHub repository usetemi/skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 563 tokens to every session, about $0.0028 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
eigent AGENTS.md
AGENTS.md instructions for eigent-ai/eigent, covering eigent agent instructions, ui work, product terminology and validation.
markifact-mcp GEMINI.md
Instructions for markifact/markifact-mcp, covering markifact, the 8 tools, discover → inspect → run, connection vs account and reporting workflow.
student-llm-wiki AGENTS.md
Instructions for IssacW228/student-llm-wiki, covering student llm wiki — agent instructions, 操作规则 operation rules, token预算规则（最高优先级）, 架构 architecture and 命令 commands.
cowork-to-code-bridge CLAUDE.md
Instructions for abhinaykrupa/cowork-to-code-bridge, covering claude.md — cowork-to-code-bridge, first connection — read this and core functions (in coworktocodebridge/client.py).
job-hunt-skills AGENTS.md
Instructions for Remotivated/job-hunt-skills, covering job hunt skills repository guidance, before editing workflows, required checks and compatibility.
myPKA CLAUDE.md
Claude Code instructions for myICOR/myPKA, covering claude.md, first run check (read this before doing anything else), identity (mandatory — applies every session), source of truth and specialist dispatch (claude code specific).