agentmods.dev

aptu-coder copilot-instructions.md

A set of repository instructions for using GitHub Copilot to handle issues and pull requests in the aptu-coder project.

In plain words
What is it for?
Assigning issues to Copilot, giving feedback on pull requests, reviewing Copilot-generated code, and checking project-specific constraints.
Why use it?
It gives reviewers and agents shared rules for checking changes, dependencies, error handling, and release steps.

Instructions file for GitHub Copilot

5 yesterday A scan 422 tokens original Apache-2.0
View the source file clouatre-labs/aptu-coder
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/clouatre-labs/aptu-coder/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/clouatre-labs/aptu-coder

Made for: GitHub Copilot.

Per session 422 This file is loaded in full into every session.
When invoked 422 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 $0.00422 $0.00422
Opus 5 $0.00211 $0.00211
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured yesterday against content hash 18a78e6c80e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aptu-coder 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 yesterday.

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 · 41 lines

What it actually says

Copilot Instructions

Assigning issues to Copilot

REST API method:

gh api repos/{owner}/{repo}/issues/{number} --method PATCH -f "assignees[]=copilot-swe-agent[bot]"

UI method: use the issue sidebar to assign to copilot-swe-agent[bot].

PR iteration

  • Comment @copilot with specific feedback; agent pushes follow-up commits
  • If unresolved after 2 iterations: close PR, amend issue, re-assign

Copilot code review

Flag:

  • Hallucinated APIs; verify against Cargo.lock and cargo doc --open
  • Scope creep beyond the issue deliverables
  • Missing error handling
  • rmcp, tree-sitter, schemars version assumptions; verify against installed versions
  • Missing cargo deny check advisories licenses run when Cargo.toml changes
  • New dependency added without justification in the PR description
  • working_dir outside the server CWD boundary accepted without error (must be rejected with INVALID_PARAMS)
  • Profile-based tool routing (APTU_CODER_PROFILE / io.clouatre-labs/profile) bypassed or ignored in tools/list
  • gh release create used instead of git tag -s vX.Y.Z -m "vX.Y.Z"
  • Tool descriptions or server instructions reference host-specific clients (e.g. "Claude Code", "Cursor")
  • Commit missing GPG signature or DCO sign-off (-S --signoff)

Design references

  • ARCHITECTURE.md - design, language handlers, "How to add a language"
  • AGENTS.md - project conventions and implementation status

Firewall

  • Copilot runs in a firewalled GitHub Actions environment; no arbitrary URLs
  • If a build step needs a URL not in the allow list, document it in the PR
  • Maintainer updates .github/copilot/firewall.yml
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. yesterday First seen · 41 lines · 422 tokens per session scan A 18a78e6c80e3

Subscribe to this mod's changes

aptu-coder copilot-instructions.md is an instructions file published in the GitHub repository clouatre-labs/aptu-coder (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 422 tokens to every session, about $0.0021 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.

Code reviewData and AILanguagesaiaptuastcall-graphcode-analysisdeveloper-tools
Related

Other instructions, from other repositories

codeweave-mcp CLAUDE.md

Instructions for semihkayan/codeweave-mcp, covering claude.md, what this project is, build & run, architecture and layers.

semihkayan/codeweave-mcp · 1,950 tokens

codexray CLAUDE.md

Instructions for NeuralRays/codexray, covering codexray — ai agent instructions, workflow and key principle.

NeuralRays/codexray · 324 tokens

graphify AGENTS.md

AGENTS.md instructions for Graphify-Labs/graphify: This project has a graphify knowledge graph at graphify-out/.

Graphify-Labs/graphify · 90 tokens

codeseek CLAUDE.md

Instructions for CodeBendKit/codeseek, covering claude.md, build & test, enter rust project directory, build and run tests.

CodeBendKit/codeseek · 1,559 tokens

arbor CLAUDE.md

Claude Code instructions for getArbor-dev/arbor, covering claude.md, commands, build, test all crates and test single crate.

getArbor-dev/arbor · 3,172 tokens

bonsai-ninja AGENTS.md

Instructions for gromhacks/bonsai-ninja, covering bonsai-ninja, map a codebase, optional explicit semantic sidecar prewarm, explicit spelling for default syntax/construct indexing and optional during active editing.

gromhacks/bonsai-ninja · 5,841 tokens