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/jl-cmd/claude-dream/copilot-instructionsgit clone --depth 1 https://github.com/jl-cmd/claude-dreamWrote 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/jl-cmd/claude-dream/copilot-instructions)<a href="https://agentmods.dev/instructions/jl-cmd/claude-dream/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jl-cmd/claude-dream/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 | $0.06006 | $0.06006 |
| Opus 5 | $0.03003 | $0.03003 |
| Sonnet 5 | $0.01201 | $0.01201 |
| Haiku 4.5 | $0.00601 | $0.00601 |
Grade C, and why
claude-dream copilot-instructions.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- AUTO-GENERATED — DO NOT EDIT. Source of truth: jl-cmd/claude-code-config/.github/copilot-instructions.md Synced by: .github/workflows/sync-ai-rules.yml Source commit: 38b416b8c92e36b43db920afd4fafce65eac6e0c Synced How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code rules for Claude, Cursor BugBot, Copilot, and other agents
This file is the canonical review-criteria instruction set for every AI agent that audits pull requests in this repository:
- Claude (PR review)
- Cursor BugBot (PR review)
- GitHub Copilot (PR review)
- Any other agent that loads
AGENTS.mdor.cursor/BUGBOT.mdfor review
These rules describe the green-light state of code in this repository. Agents apply them to the lines a PR adds or modifies, surface deviations as findings, and recommend corrections. Output is review feedback.
Where a rule lists exemptions (test files, migrations, config files), the exemption applies. Where a rule shows a before/after pair, the "after" form is the green-light pattern.
This file is rules-only. Repo layout, build commands, and workflow guidance live elsewhere.
Surface map: this file is the canonical human and AI code-quality review contract. packages/claude-dev-env/docs/CODE_RULES.md is its compact projection. packages/claude-dev-env/hooks/blocking/code_rules_enforcer.py is hand-maintained production enforcement (not generated from this file). .cursor/BUGBOT.md is a sync projection of this file. Session policies (question routing, task tracking) live under packages/claude-dev-env/rules/ — see rules/code-standards.md.
Contents
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 · 212 lines · 6,006 tokens per session scan C 0e0b07714515
claude-dream copilot-instructions.md is an instructions file published in the GitHub repository jl-cmd/claude-dream (12 stars, last pushed 24d ago), licensed MIT. It adds 6,006 tokens to every session, about $0.0300 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.