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/srnichols/plan-forge/copilot-instructionsgit clone --depth 1 https://github.com/srnichols/plan-forgeWhat 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 | $0.02670 | $0.02670 |
| Opus 5 | $0.01335 | $0.01335 |
| Sonnet 5 | $0.00534 | $0.00534 |
| Haiku 4.5 | $0.00267 | $0.00267 |
Grade A, and why
plan-forge 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.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for Copilot
Project: Stack: Last Updated:
Architecture Principles
BEFORE making ANY code changes, read: .github/instructions/architecture-principles.instructions.md
Core Principles (Non-Negotiable)
- Architecture-First — Ask 5 questions before coding
- Separation of Concerns — Controller → Service → Repository
- Best Practices Over Speed — Enterprise-grade, not hacky
- TDD for Business Logic — Red-Green-Refactor
- Type Safety — Explicit types everywhere
Cost estimates
Cost estimates come from tools, not from chat math. When the user asks "how much will this plan cost?" or when you present any quorum-mode picker showing dollar amounts, you MUST call one of these tools first:
forge_estimate_quorum— projected cost of a plan under all four quorum modes (auto,power,speed,false) in one payload. Call this before showing any picker or decision matrix.forge_cost_report— actuals from previous runs (token counts, per-model spend, monthly aggregates).
Do not hand-compute quorum costs, do not invent dollar amounts in chat, and do not synthesize picker UIs without tool-backed numbers. Hand-computed quorum estimates have been observed to overshoot reality by an order of magnitude.
Talking to Forge-Master
For open-ended reasoning, use forge_master_ask instead of chaining
tools yourself. Forge-Master classifies your intent, fetches memory
context, and orchestrates read-only tool calls on your behalf.
- Use it for: multi-step reasoning about plans, troubleshooting failures, querying run status, funneling ideas into Crucible smelts.
- Don't use it for: direct file edits or code generation — Forge-Master is read-only.
- Example:
forge_master_ask({ message: "Why did Phase-27 Slice 4 fail?" })— Forge-Master callsforge_watch_live,brain_recall, andforge_bug_listto build an answer.
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 · 257 lines · 2,670 tokens per session scan A 624f88b84a33
plan-forge copilot-instructions.md is an instructions file published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 22d ago), licensed MIT. It adds 2,670 tokens to every session, about $0.0134 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
dotnet-skills AGENTS.md
Instructions for managedcode/dotnet-skills, covering agents.md, purpose, solution topology, rule precedence and path and linking rules.
dotnet-skills copilot-instructions.md
Instructions for managedcode/dotnet-skills: Use AGENTS.md as the repository-wide source of truth for workflow, catalog structure, release policy, and skill maintenance rules.
Perigon.CLI copilot-instructions.md
Instructions for AterDev/Perigon.CLI, covering github copilot instructions, general guidelines, 技术栈, 项目结构与分层 and 代码风格约定.
copilot-instructions copilot-instructions.md
Instructions for SebastienDegodez/copilot-instructions, covering copilot instructions, language policy, development code generation and workflow implementation.
maf-doctor maf-deployment.instructions.md
Always-loaded production-deployment patterns for MAF 1.3.0. Auto-applies to Program.cs, DI registration files, and infra config. Covers ManagedIdentityCredential, MaxTokens caps, secret handling, OpenTelemetry wiring, and the analyzer rules that catch regressions at write time.
maf-doctor copilot-instructions.md
Instructions for joslat/maf-doctor, covering maf 1.3.0 migration — auto-loaded constraints, maf 1.3.0 — constraints & breaking changes reference, hard constraints (never violate), fan-out / fan-in rules (silent failure risk) and key breaking changes.