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/omkhar/vulnerability-validation-skill/copilot-instructionsgit clone --depth 1 https://github.com/omkhar/vulnerability-validation-skillWhat 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 | $0.00547 | $0.00547 |
| Opus 5 | $0.00273 | $0.00273 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
vulnerability-validation-skill copilot-instructions.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.
What it actually says
Copilot Repository Instructions
This is the repo-wide GitHub Copilot instruction surface for this repository. GitHub Copilot is a first-party supported agent surface here. This file is generated from canonical repository guidance, not an edit source.
Before changing this repository:
- Treat
skill-core/vulnerability-validation.md,skill-core/references/,skill.json, andAGENTS.mdas canonical sources. - Treat
.agents/skills/,.agent/skills/,.claude/skills/,.gemini/skills/,CLAUDE.md,GEMINI.md, and.github/copilot-instructions.mdas generated surfaces. - Treat Copilot as first-party alongside Codex, Claude Code, Gemini CLI, and Google Antigravity; use this repo-wide file plus
AGENTS.md,CLAUDE.md, orGEMINI.mdwhen the Copilot surface supports agent instructions. - For discovering new vulnerabilities (0-days) in a target repository and validating them — by default native discovery when no findings list exists, with a supplied scanner/researcher corpus as an optional seed, never a substitute for the mandatory native sweep — use the same canonical workflow as the supported agent surfaces: load
skill-core/vulnerability-validation.mdand the relevant files underskill-core/references/before planning, triaging, patching, or writing maintainer-facing evidence. - Load
skill-core/vulnerability-validation.mdand relevant files underskill-core/references/before changing validation workflow semantics. - Include a cross-agent adversarial skill-optimization review for Codex, Claude Code, Gemini CLI, GitHub Copilot, and Google Antigravity in
reviews/for substantive skill or surface changes; cover trigger precision, prompt/context budget, duplicate/drifted surfaces, progressive disclosure, supported OS/shell/path/profile assumptions, and deletion/edit safety. - After editing the canonical skill, shared metadata, references, or
AGENTS.md, runmake sync; before opening a PR, runmake verify, or use the README's platform-equivalent Python commands on hosts withoutmake. - Keep portable instructions concise and move detailed schemas to
skill-core/references/. - Do not add target-repo-specific findings, local absolute paths, private advisory details, secrets, or machine-specific setup.
- Record local role-lens consensus in
reviews/for workflow semantics, artifact contracts, generated surfaces, or maintainer-facing text changes.
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 · 20 lines · 547 tokens per session scan A 9a30fb1e4ca9
vulnerability-validation-skill copilot-instructions.md is an instructions file published in the GitHub repository omkhar/vulnerability-validation-skill (5 stars, last pushed 9d ago), licensed Apache-2.0. It adds 547 tokens to every session, about $0.0027 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.