Borrowing it
Nothing to install: this file belongs to WhatIfWeDigDeeper/agent-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/WhatIfWeDigDeeper/agent-skills/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/WhatIfWeDigDeeper/agent-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/whatifwedigdeeper/agent-skills/copilot-instructions)<a href="https://agentmods.dev/instructions/whatifwedigdeeper/agent-skills/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/whatifwedigdeeper/agent-skills/copilot-instructions/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/whatifwedigdeeper/agent-skills/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/whatifwedigdeeper/agent-skills/copilot-instructions.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 | $0.11923 | $0.11923 |
| Opus 5.5 | $0.04769 | $0.04769 |
| Sonnet 5.5 | $0.02385 | $0.02385 |
| Haiku 4.5 | $0.01192 | $0.01192 |
Grade E, and why
agent-skills copilot-instructions.md scanned grade E with 4 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 1mo 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **Tests that run `git` in a temp dir must strip `GIT_*` from the subprocess env** — git exports `GIT_DIR`/`GIT_WORK_TREE` to hook subprocesses, overriding `cwd=`, so it operates on the real repo. Use `env={k: v for k, Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **`git worktree remove` does not delete the directory or local branch**: use `-f -f` (overrides agent-isolation lock), then `rm -rf <path>` and `git branch -D <branch>`. **In sandbox mode the directory delete fails "Op Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Check the pinned scanner version against PyPI when entering `evals/security/`.** `snyk-agent-scan` has no auto-update mechanism — compare `SCANNER_PKG` in `scan.sh` against `curl -sS https://pypi.org/pypi/snyk-agent- Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **GraphQL queries with `!` type markers cannot be passed as inline shell strings in zsh** — `String!`, `Int!`, etc. trigger history expansion and produce `UNKNOWN_CHAR` errors from `gh api graphql`. Pass the query via Copies of this mod
1 near-identical copy found in the catalogue:
- agent-skills CLAUDE.md — 86% identical, 291 lines differ
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions
Keep CLAUDE.md in sync: whenever you add, update, or remove a rule in this file, apply the equivalent change to the appropriate CLAUDE.md — the root CLAUDE.md for repo-wide rules, or a subdirectory CLAUDE.md (e.g. skills/CLAUDE.md, evals/CLAUDE.md, tests/CLAUDE.md, specs/CLAUDE.md) for context-specific rules (skill authoring, eval benchmarks, test conventions, spec editing). Claude Code auto-loads subdirectory CLAUDE.md files when working in those directories; Copilot has only one instructions file, so all rules — including those whose canonical home is a subdirectory CLAUDE.md — must also appear here; a rule dropped from a CLAUDE.md because a subdirectory CLAUDE.md covers it stays here. The two assistants (Copilot vs. Claude Code) should encode the same project conventions. When running /learn in this project, always update both the appropriate CLAUDE.md and .github/copilot-instructions.md without asking which to update. The instruction-sync CI check enforces this pairing for any CLAUDE.md path in the repo — it does not compare the two files' content.
Project Overview
Evals belong under evals/ at the repo root, not inside skill directories — they are development artifacts and should not be bundled when a skill is distributed.
Core Editing Rules
- Keep instructions assistant-neutral unless a tool or platform detail is inherently assistant-specific.
- Skill description has a 500-character hard limit — the
descriptionfield in SKILL.md frontmatter is capped at 500 characters by the skills runtime. Keep descriptions concise; count characters before finalizing. - Preserve the existing workflow style in
SKILL.md: numbered process sections, executable bash blocks, tables where useful, and examples where useful. - When substantially modifying a skill, update its
README.mdentry and notes. - Bump
metadata.versionon everySKILL.mdchange or reference-file change that affects the skill. - On an active PR branch, re-run the check below before committing any
SKILL.mdchange — not just when you intend to bump — to confirm no bump already exists relative toorigin/main:
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.
- 1mo ago Changed · -2 tokens per session 6123f7a215c7
- 2mo ago First seen · 232 lines · 11,925 tokens per session scan E e54390dbf0f7
agent-skills copilot-instructions.md is an instructions file published in the GitHub repository WhatIfWeDigDeeper/agent-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 11,923 tokens to every session, about $0.0477 per session on Opus 5.5. A static security scan graded it E with 4 findings (harvests environment variables, recursive force delete, makes network calls). 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.