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/talberthoule/backchannel/agents-mdgit clone --depth 1 https://github.com/talberthoule/backchannelWrote 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/talberthoule/backchannel/agents-md)<a href="https://agentmods.dev/instructions/talberthoule/backchannel/agents-md"><img src="https://agentmods.dev/badge/instructions/talberthoule/backchannel/agents-md.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 | $0.03831 | $0.03831 |
| Opus 5 | $0.01916 | $0.01916 |
| Sonnet 5 | $0.00766 | $0.00766 |
| Haiku 4.5 | $0.00383 | $0.00383 |
Grade B, and why
backchannel AGENTS.md scanned grade B 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Sentrux is installed at `C:/Users/thoule/.local/bin/sentrux.exe` and configured as a Codex MCP server in `C:/Users/thoule/.codex/config.toml`. How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with this repository.
Current Codebase Snapshot
Backchannel (formerly Call Helper) is a real-time meeting analysis app. A React frontend captures microphone audio as PCM16 16 kHz mono and streams it over WebSocket. The FastAPI backend writes speaker-attributed transcript entries, runs Gemini-based analysis agents over recent transcript text, and stores insights in PostgreSQL.
Backend tests live in backend/tests/ as stdlib unittest files; run them from backend/ with python -m unittest discover -s tests. Desktop tests use the same runner from desktop/, and frontend behavior checks use npm run build for typechecking and bundling.
Build & Run
Sentrux Structural Analysis
Sentrux is installed at C:/Users/thoule/.local/bin/sentrux.exe and configured as a Codex MCP server in C:/Users/thoule/.codex/config.toml.
sentrux . # Open the GUI for this repo
sentrux check . # Enforce .sentrux/rules.toml
sentrux gate . # Compare current structure against .sentrux/baseline.json
sentrux gate --save . # Refresh the structural baseline after intentional architecture changes
Current baseline quality is 6469, with coupling 0.06, 0 cycles, 2 god files, and 35 complex functions. The rules are calibrated to the existing codebase; tighten max_cc, max_fn_lines, and max_file_lines after refactoring current hotspots.
The baseline records the structural metrics used by sentrux gate. sentrux check . is expected to report only the two approved generated lockfile exceptions documented next to max_file_lines in .sentrux/rules.toml; any other finding must be fixed before the baseline is refreshed.
Docker Compose (primary)
docker-compose up --build
docker-compose down -v
- Frontend: http://localhost:3000
- Backend container: http://localhost:8001
- Frontend nginx proxies API and WebSocket traffic from :3000 to backend :8000
- Database: PostgreSQL 16 on host port 5432
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.
- 3d ago First seen · 291 lines · 3,831 tokens per session scan B 4156986cd5e2
backchannel AGENTS.md is an instructions file published in the GitHub repository talberthoule/backchannel (5 stars, last pushed 17d ago), licensed MIT. It adds 3,831 tokens to every session, about $0.0192 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
CLIProxyAPI AGENTS.md
AGENTS.md instructions for router-for-me/CLIProxyAPI, covering agents.md, repository, commands, config and architecture.
vexa AGENTS.md
AGENTS.md instructions for Vexa-ai/vexa, covering agents.md — the agent front door (in-repo), researching vexa? start here, driving vexa from an agent session, your issue is your prd and claiming — and say hello on discord.
neo-chat AGENTS.md
AGENTS.md instructions for u14app/neo-chat, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
proxypal AGENTS.md
Instructions for heyhuynhgiabuu/proxypal, covering proxypal, stack, structure, commands and code style.
vexa CLAUDE.md
Claude Code instructions for Vexa-ai/vexa, a project described as: Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.