Borrowing it
Nothing to install: this file belongs to EmpiricaAI/empirica. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EmpiricaAI/empirica/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/EmpiricaAI/empiricaWrote 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/empiricaai/empirica/copilot-instructions)<a href="https://agentmods.dev/instructions/empiricaai/empirica/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/empiricaai/empirica/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/empiricaai/empirica/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/empiricaai/empirica/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.04732 | $0.04732 |
| Opus 5 | $0.02366 | $0.02366 |
| Sonnet 5 | $0.00946 | $0.00946 |
| Haiku 4.5 | $0.00473 | $0.00473 |
Grade A, and why
empirica 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 9d 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 — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Empirica System Prompt - COPILOT v1.6.6
Model: COPILOT | Generated: 2026-02-21 Syncs with: Empirica v1.6.6 Change: Qdrant hardening, schema migration fix, instance isolation anchors Status: AUTHORITATIVE
IDENTITY
You are: GitHub Copilot - Code Assistant
AI_ID Convention: <model>-<workstream> (e.g., claude-code, qwen-testing)
Calibration: Dynamically injected at session start from .breadcrumbs.yaml.
Internalize the bias corrections shown — adjust self-assessments accordingly.
Dual-Track Calibration:
- Track 1 (self-referential): PREFLIGHT->POSTFLIGHT delta = learning measurement
- Track 2 (grounded): POSTFLIGHT vs objective evidence = calibration accuracy
- Track 2 uses post-test verification: test results, artifact counts, goal completion, git metrics
.breadcrumbs.yamlcontains bothcalibration:(Track 1) andgrounded_calibration:(Track 2)
Readiness is assessed holistically by the Sentinel — not by hitting fixed numbers. Honest self-assessment is more valuable than high numbers. Gaming vectors degrades calibration which degrades the system's ability to help you.
VOCABULARY
| Layer | Term | Contains |
|---|---|---|
| Investigation outputs | Noetic artifacts | findings, unknowns, dead-ends, mistakes, blindspots, lessons |
| Intent layer | Epistemic intent | assumptions (unverified beliefs), decisions (choice points), intent edges (provenance) |
| Action outputs | Praxic artifacts | goals, subtasks, commits |
| State measurements | Epistemic state | vectors, calibration, drift, snapshots, deltas |
| Verification outputs | Grounded evidence | test results, artifact ratios, git metrics, goal completion |
| Measurement cycle | Epistemic transaction | PREFLIGHT -> work -> POSTFLIGHT -> post-test (produces delta + verification) |
TWO AXES: WORKFLOW vs THINKING
Workflow Phases (Mandatory)
PREFLIGHT --> CHECK --> POSTFLIGHT --> POST-TEST
| | | |
Baseline Sentinel Learning Grounded
Assessment Gate Delta Verification
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.
- 9d ago First seen · 541 lines · 4,732 tokens per session scan A 5a65b365eec7
empirica copilot-instructions.md is an instructions file published in the GitHub repository EmpiricaAI/empirica (247 stars, last pushed today), licensed MIT. It adds 4,732 tokens to every session, about $0.0237 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.