Borrowing it
Nothing to install: this file belongs to gear-foundation/vara-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gear-foundation/vara-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/gear-foundation/vara-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/gear-foundation/vara-skills/agents-md)<a href="https://agentmods.dev/instructions/gear-foundation/vara-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/gear-foundation/vara-skills/agents-md/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/instructions/gear-foundation/vara-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/gear-foundation/vara-skills/agents-md.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 | $0.00278 | $0.00278 |
| Opus 5.5 | $0.00111 | $0.00111 |
| Sonnet 5.5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
vara-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 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.
What it actually says
AGENTS.md
Purpose
This repository is the provisional product repo for a portable Vara Sails-builder skill pack. It owns builder-facing skill content, shared references, validation scripts, and installation surfaces for Codex first, with Claude and OpenClaw packaging added in-repo.
Working Rules
- Use
writing-skillsbefore creating or editing any skill inskills/. - Apply TDD to repository behavior: add or update tests before changing scripts, validation logic, or published skill contracts.
- Keep each skill directory flat and include
SKILL.md,assets/,references/, andscripts/. - Prefer shared repository references in
references/and shared templates inassets/; skill files may reference them via relative paths. - Do not embed machine-specific absolute paths in published docs or skills unless the file is an explicit local validation target.
- Treat the current public skill catalog as provisional until the sibling eval repo proves which candidate skills create real uplift.
- Keep the first builder path focused on standard Gear/Vara Sails, not Vara.eth-first workflows.
Verification
- Run
make verifybefore claiming the repo is ready. - Keep installation working through
scripts/install-codex-skills.sh. - Keep repository docs aligned with the product split: this repo owns skills and packaging; the sibling eval repo owns measurement.
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 · 19 lines · 278 tokens per session scan A 4d883bf6dba9
vara-skills AGENTS.md is an instructions file published in the GitHub repository gear-foundation/vara-skills (17 stars, last pushed 3mo ago), licensed MIT. It adds 278 tokens to every session, about $0.0011 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.
vara-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vara-skills AGENTS.mdgear-foundation/vara-skills | Instructions file | 17 | 3mo ago | MIT | A | 278 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |