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/andurilcode/accordo/copilot-instructionsgit clone --depth 1 https://github.com/AndurilCode/accordoWhat 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 | $0.00821 | $0.00821 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
accordo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- accordo CLAUDE.md — 94% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions
Task Execution Guidelines
🚨 MANDATORY WORKFLOW COMPLIANCE 🚨
Before starting ANY task, evaluate it using these criteria:
Use Workflow Tools When:
- Task involves multiple steps or phases
- Task requires coordination across multiple files
- Task involves creating, modifying, or analyzing code structures
- Task requires planning, analysis, or systematic approach
- Task involves debugging, testing, or validation
- Task creates new features, components, or systems
- When in doubt, ALWAYS use workflows
Only Skip Workflows For:
- Single mathematical calculations
- One-line explanations or definitions
- Direct copy/paste operations
- Immediate answers to factual questions
🔄 MANDATORY WORKFLOW ENTRY PROCESS
⚠️ NON-NEGOTIABLE: For ALL qualifying tasks, you MUST follow this exact sequence:
STEP 1: DISCOVER (REQUIRED FIRST STEP)
workflow_discovery(task_description="[Exact user request]")
Purpose: View all available YAML workflows and their capabilities Result: List of workflows with descriptions and suitability assessment
STEP 2: CHOOSE AND START (REQUIRED SECOND STEP)
workflow_guidance(action="start", context="workflow: [Selected Workflow Name]")
Purpose: Initialize the selected workflow session Result: Workflow begins with first phase instructions
STEP 3: FOLLOW SCHEMA (ONGOING)
workflow_guidance(action="next", context='{"choose": "[option]", "criteria_evidence": {"criterion": "detailed evidence"}}')
Purpose: Navigate through workflow phases using YAML-defined transitions with detailed evidence Result: Structured progression through the complete workflow with work tracking
🎯 Decision Framework
Use this exact decision tree for EVERY user request:
-
Is this a single, immediate action?
- YES: Proceed directly (rare cases only)
- NO: Go to Step 2
-
Does the task involve ANY of these?
- Multiple files or components? → USE WORKFLOW
- Planning or analysis phase? → USE WORKFLOW
- Code creation or modification? → USE WORKFLOW
- Testing or validation? → USE WORKFLOW
- Debugging or troubleshooting? → USE WORKFLOW
- Documentation or explanation? → USE WORKFLOW
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 · 89 lines · 821 tokens per session scan A 2e0cc09e1864
accordo copilot-instructions.md is an instructions file published in the GitHub repository AndurilCode/accordo (5 stars, last pushed 10mo ago), licensed MIT. It adds 821 tokens to every session, about $0.0041 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
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
omnigent copilot-instructions.md
Copilot instructions for omnigent-ai/omnigent, covering copilot code review instructions, e2e test requirement, backend test coverage and frontend test coverage.
AutoAgents AGENTS.md
Instructions for liquidos-ai/AutoAgents, covering autoagents repository guidelines, project structure & module organization, code quality, naming conventions and error handling.
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).