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/ebibibi/ebi-agent-chat-relay/copilot-instructionsgit clone --depth 1 https://github.com/ebibibi/ebi-agent-chat-relayWrote 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/ebibibi/ebi-agent-chat-relay/copilot-instructions)<a href="https://agentmods.dev/instructions/ebibibi/ebi-agent-chat-relay/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ebibibi/ebi-agent-chat-relay/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 | $0.00426 | $0.00426 |
| Opus 5 | $0.00213 | $0.00213 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
ebi-agent-chat-relay 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 5d 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.
What it actually says
claude-code-discord-bridge — Copilot Instructions
Discord frontend for Claude Code CLI. Python 3.12+ with discord.py v2.
Key Rules
- Type hints required on all function signatures
from __future__ import annotationsin every Python file- ruff for linting and formatting (line-length: 100)
- pytest with pytest-asyncio (auto mode) for testing
- Never use
shell=Truein subprocess calls — alwayscreate_subprocess_exec - Validate all user input before passing to CLI (regex for session IDs, skill names)
--separator before user prompts in CLI args to prevent flag injectioncontextlib.suppressfor non-critical Discord API failures- Logging via
logging.getLogger(__name__), neverprint()
Architecture
claude_discord/claude/— CLI subprocess runner and stream-json parserclaude_discord/cogs/— Discord.py Cogs. Use_run_helper.run_claude_in_thread()for CLI executionclaude_discord/database/— SQLite session persistence (aiosqlite)claude_discord/discord_ui/— Status reactions, message chunking, embedstests/— pytest suite
Testing (TDD Enforced)
Write tests FIRST, then implement. Follow RED → GREEN → REFACTOR for all new features and bug fixes.
uv run pytest tests/ -v --cov=claude_discord
uv run ruff check claude_discord/
uv run ruff format --check claude_discord/
Security (Mandatory Pre-Commit)
This project spawns Claude Code CLI as a subprocess. All user input flows through to CLI args. Never interpolate user input into shell commands. Strip secrets from subprocess env. Run security audit before committing changes to runner.py, _run_helper.py, or any Cog.
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.
- 5d ago First seen · 40 lines · 426 tokens per session scan A 833baceb7fa6
ebi-agent-chat-relay copilot-instructions.md is an instructions file published in the GitHub repository ebibibi/ebi-agent-chat-relay (57 stars, last pushed 2d ago), licensed MIT. It adds 426 tokens to every session, about $0.0021 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
switch CLAUDE.md
Claude Code instructions for sandbox-quantum/switch, covering claude.md, this repository is public, project overview, switch console and common commands.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
nexu AGENTS.md
Instructions for nexu-io/nexu, covering agents.md, repo overview, project overview, commands and branch model.
cc-plugin-codex AGENTS.md
AGENTS.md instructions for sendbird/cc-plugin-codex, a project described as: An open-source plugin that runs inside Codex and lets you use Claude Code and Claude models for review, rescue, and tracked background workflows.
codex-usage-widget AGENTS.md
Instructions for ognjeeen/codex-usage-widget, covering agents.md, project, scope and decision discipline, authorization and repository safety and architecture boundaries.
codex-project-skill-manager AGENTS.md
Instructions for WildPigKing/codex-project-skill-manager, covering codex project & skill manager, product boundary, startup routing, consent contract and repository records.