Borrowing it
Nothing to install: this file belongs to gosha70/code-copilot-team. 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/gosha70/code-copilot-team/master/adapters/github-copilot/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote 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/gosha70/code-copilot-team/copilot-instructions)<a href="https://agentmods.dev/instructions/gosha70/code-copilot-team/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/gosha70/code-copilot-team/copilot-instructions.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 5.1 | $0.06264 | $0.06264 |
| Opus 5 | $0.03132 | $0.03132 |
| Sonnet 5 | $0.01253 | $0.01253 |
| Haiku 4.5 | $0.00626 | $0.00626 |
Grade C, and why
code-copilot-team copilot-instructions.md scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Any destructive command: rm -rf, DROP TABLE, TRUNCATE, git reset --hard, git push --force. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Execute your own test plan.** If you write test commands (curl, bash, docker, etc.) as part of a build summary, run every command yourself and report results before declaring done. How it starts
The opening of the file, as written. The whole thing — 575 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions
Auto-generated from shared/skills/. Do not edit directly. Regenerate with: ./scripts/generate.sh
Coding Standards
Applied to all code generation and review sessions.
Quality Gates (enforce before merge/commit)
- Lint errors: 0
- Test coverage: >= 80% (critical paths >= 95%)
- No commented-out code
- No unused imports or dead code
- No hard-coded secrets or credentials
Prohibited Patterns
- No hard-coded structured data (JSON/XML literals) inside source — use config files or env vars. This includes default values on Python dataclasses/Pydantic models and equivalents in other languages — define only the schema in code; put actual defaults in
config/defaults.yaml(or equivalent). A config loader reads the file and populates the schema; env vars or override files layer on top. - No magic numbers or strings — use named constants. When a string key crosses a module boundary (config key, variable name, prompt template name), define it as a constant in the lowest common ancestor package and import it everywhere. A hardcoded string in two modules is a silent breakage waiting to happen.
- No secrets in source — use env vars or a secrets manager.
- No print() debugging in committed code — use structured logging.
- No wildcard imports.
- No bare except / catch without specific exception types.
- No SQL string concatenation — use parameterized queries.
Verification Discipline
- Never suggest skipping a failing verification step. When a test, build, lint check, Docker build, or script execution fails, diagnose and fix the issue. Do not suggest workarounds that bypass the deliverable.
- Execute your own test plan. If you write test commands (curl, bash, docker, etc.) as part of a build summary, run every command yourself and report results before declaring done.
- Build it, run it. Any executable artifact you create (Dockerfile, shell script, CI workflow, launcher flag) must be executed at least once before committing. Syntax validity alone is not sufficient.
- Re-review after fix. After applying a fix for a bug flagged in code review or a reviewer note, run the review process again (e.g.,
/team-reviewor the equivalent specialist agent) before declaring done. Do not just apply the fix and move on — the re-review may catch secondary issues exposed by the fix itself. - Confirm against origin before declaring done. Run
scripts/check-origin-alignment.sh <feature-id>before presenting any feature for review. Exit ≥ 2 means the working artifact has drifted from the user's origin and you must surface the three-resolution escalation (rescope / restart / document divergence) — do not proceed. Seeshared/skills/origin-confirmation/SKILL.mdfor the full protocol.
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 Changed · +14 lines · +130 tokens per session b4df572dcbd0
- 3d ago First seen · 561 lines · 6,134 tokens per session scan C ba04d1cdbdee
code-copilot-team copilot-instructions.md is an instructions file published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed yesterday), licensed MIT. It adds 6,264 tokens to every session, about $0.0313 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
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.
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.
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).
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.