anchor copilot-instructions.md

Coding instructions for the Anchor project, including required reading, testing rules, cleanup checks, documentation requirements, and limits on pull-request size. Test-first development, or TDD, means writing a test before the code that makes it pass.

In plain words
What is it for?
Preparing code changes, writing tests first, running linting and type checks, updating architecture notes, and creating commits that explain the reason for the change.
Why use it?
They give an agent a fixed order of checks and project rules before it changes code. This helps catch unused code, type errors, formatting problems, missing documentation, and overly large changes.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/peva3/anchor/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/peva3/anchor

Made for: GitHub Copilot.

Per session 683 This file is loaded in full into every session.
When invoked 683 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00683 $0.00683
Opus 5 $0.00342 $0.00342
Sonnet 5 $0.00137 $0.00137
Haiku 4.5 $0.00068 $0.00068

Measured 2d ago against content hash 834159f04c9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anchor 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.

.github/copilot-instructions.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions

All project rules are defined in AGENTS.md. Read it before writing any code.

Required Reading

Before any task, read these files:

  • AGENTS.md — All project rules and conventions
  • DEEPDIVE.md — System architecture narrative
  • docs/ — Project documentation

Critical Rules

  1. No dead code — Remove unused functions, imports, variables immediately (Section 1)
  2. Test-first — Write tests before code, verify all pass before committing (Section 8)
  3. Full cleanup sweep before every commit:
    ruff check . && ruff format . && vulture . && mypy .
    
  4. tests/ folder — All tests and random scripts go here; always in .gitignore (Section 5)
  5. docs/ and research/ — Create for every new project (Section 5)
  6. Human-sounding commits — Explain WHY changes were made, not just WHAT changed (Section 15)
  7. DEEPDIVE.md — Update after any architectural change (Section 5)
  8. PR size limit — 800 lines max, 500 for complex logic (Section 33)
  9. Decision ladder — YAGNI → stdlib → native → existing dep → one line → minimum (Section 50.1)
  10. Tradeoff comments — Name the ceiling and upgrade trigger for any intentional shortcut (Section 50.2)
  11. Pre-commit hooks mandatory — Install and run before every commit (Section 37)

Prohibited Actions

  • NEVER create PRs, issues, or GitHub activity without explicit user approval (Section 2)
  • NEVER leave dead code, stubs, or silent exception handlers (Section 1)
  • NEVER commit without running the full lint/vulture sweep first (Section 9)
  • NEVER skip pre-commit hooks (Section 37)
  • NEVER submit a PR over 800 lines (Section 33)

Project Structure

project/
├── src/              # Source code
├── tests/            # All tests (gitignored)
├── docs/             # Architecture docs
├── research/         # Research files
├── DEEPDIVE.md       # System narrative
├── AGENTS.md         # This file (entry point)
├── skills/           # Full rule text — lazy-loaded by task
└── TODO.md           # Task tracking

Read the full file on GitHub · 64 lines

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.

  1. 2d ago First seen · 64 lines · 683 tokens per session scan A 834159f04c9d

Subscribe to this mod's changes

anchor copilot-instructions.md is an instructions file published in the GitHub repository peva3/anchor (8 stars, last pushed 13d ago), licensed MIT. It adds 683 tokens to every session, about $0.0034 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.