Borrowing it
Nothing to install: this file belongs to vraj-ai/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/vraj-ai/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/vraj-ai/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/vraj-ai/skills/agents-md)<a href="https://agentmods.dev/instructions/vraj-ai/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vraj-ai/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/vraj-ai/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vraj-ai/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 | $0.00487 | $0.00487 |
| Opus 5.5 | $0.00195 | $0.00195 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
skills AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
skills
vskills catalogue and installer for vraj-ai/skills. Node >= 18. npm test runs the suite. node scripts/validate-skills.mjs lints skill frontmatter and cross-references.
Which skill
pstack /poteto-mode is the inner loop: understand, design, build, verify, interrogate, ship. Install pstack beside this catalogue. Do not copy it into the repo. These skills own the queue and delivery.
- Any task:
/ship. A feature runs/recall,/howand/why,/teach,/architect,/grillfor product questions, and/issuesinside/ship, builds with/poteto-mode's Feature or Bug-fix playbook, proves the change with the repo'sverify-<app>skill, and hands off to/land. A medium change runs/how, one issue, build, prove, and review. A small change goes straight to the build. - Product questions only:
/grill. Agreed work to queue without building:/issues. When a repo has averify-<app>skill, name that feature in Verification. - Stopping before done:
/snapshotcompletes the ship record ($(git rev-parse --git-common-dir)/vskills/ship/<slug>.md, never committed)./resume-workcontinues at its phase. An in-chat catch-up maps to pstack/ketchup. - Merge is
/land, and only with explicit authority. Self-merge is off (fleet ADR 0003).
/route maps an intent to one of these. It must not send the same request to both /ship and /poteto-mode.
Verify
Before claiming this repo works, run .cursor/skills/verify-skills: node scripts/validate-skills.mjs, then npm test. Paste both summaries. A model verdict is not a pass.
Tracker and context
GitHub Issues on vraj-ai/skills via gh. This repo does not commit docs/ or CONTEXT/ (see setup-vskills). Consumer projects keep durable decisions in their own CONTEXT/architecture.md.
Authority
Do not merge, force-push main, or commit secrets. Opening a PR is the delivery.
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 Changed · +17 tokens per session c73ea7091b56
- 6d ago Changed · -1 lines · +36 tokens per session 857061e969ad
- 14d ago Changed · +4 lines · +258 tokens per session e51137546b7c
- 2mo ago First seen · 24 lines · 176 tokens per session scan A 78757486bd8b
skills AGENTS.md is an instructions file published in the GitHub repository vraj-ai/skills (4 stars, last pushed yesterday), licensed MIT. It adds 487 tokens to every session, about $0.0019 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.