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/girishr/specpilot/copilot-instructionsgit clone --depth 1 https://github.com/girishr/SpecPilotWrote 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/girishr/specpilot/copilot-instructions)<a href="https://agentmods.dev/instructions/girishr/specpilot/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/girishr/specpilot/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 | $0.00830 | $0.00830 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
SpecPilot 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Coding Instructions — SpecPilot
This file is automatically read by GitHub Copilot, Cursor, and other AI tools on every request. Keep this file short — only critical mandates. Full context is in
.specs/project/project.yaml.
Project
- Name: SpecPilot
- Stack: TypeScript / Node.js / Commander.js
- Specs location:
.specs/
🔴 Critical Mandates — Never violate, no exceptions
- NEVER commit code to git unless the developer explicitly asks. Always ask first.
- NEVER push to git unless the developer explicitly asks. Always ask first.
- NEVER deploy, publish, or release the project unless the developer explicitly asks. Always ask first.
- NEVER modify the
.specs/folder structure, subfolder names, or file names. Only update file contents. - ALWAYS update affected
.specs/files after every code change — without being asked:- Structural changes →
architecture/architecture.md - Feature changes →
project/requirements.md - Test changes →
quality/tests.md - Task status →
planning/tasks.md - Completed work →
CHANGELOG.md
- Structural changes →
- NEVER describe, quote, or reference file contents without first reading the file via a tool call in this session. If you have not read the file yet, say so explicitly before answering.
- NEVER implement, write code, or make file changes unless the developer explicitly asks. If the next step seems obvious, ask first — do not assume.
- SPEC-FIRST review gate: Before touching any code or non-spec files, read all relevant
.specs/files, update all affected spec files first, present a Spec Report summarizing what changed, which files were affected, and what the specs now say, then wait for the developer's explicityes, proceedbefore writing code. If the developer declines, revert the spec changes and stop.
🟡 Process Mandates
- Spec-First: Update
.specs/before writing code. - Log all AI interactions in
.specs/development/prompts.mdwith timestamps. - Document decisions in
.specs/development/context.md.
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.
- 4d ago First seen · 69 lines · 830 tokens per session scan A 2dc4cf321e6d
SpecPilot copilot-instructions.md is an instructions file published in the GitHub repository girishr/SpecPilot (37 stars, last pushed 1mo ago), licensed MIT. It adds 830 tokens to every session, about $0.0042 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 2026-08-30.
Other instructions, from other repositories
ai-development-patterns CLAUDE.md
Claude Code instructions for PaulDuvall/ai-development-patterns, covering claude.md, repository overview, repository structure, key architectural principles and pattern architecture.
ai-development-patterns AGENTS.md
AGENTS.md instructions for PaulDuvall/ai-development-patterns, covering agent instructions, task tracking, pattern adoption evaluation and landing the plane (session completion).
whoop-mcp CLAUDE.md
Claude Code instructions for shashankswe2020-ux/whoop-mcp, covering project: whoop-mcp, tech stack, commands, project structure and code conventions.
huly-mcp CLAUDE.md
Instructions for dearlordylord/huly-mcp, covering project instructions, design principle: llm-first api, project harness (copy to new projects), package manager and verification.
gsd-task-manager CLAUDE.md
Claude Code instructions for vscarpenter/gsd-task-manager, covering claude.md, project overview, design context, core commands and development.
FrameCode-VibeWork AGENTS.md
AGENTS.md instructions for Sistema2D/FrameCode-VibeWork, covering agents.md, instruction order, reading-trigger rule, regression rule and when a plan is required.