Borrowing it
Nothing to install: this file belongs to gaijinjoe/herdres. 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/gaijinjoe/herdres/main/AGENTS.mdgit clone --depth 1 https://github.com/gaijinjoe/herdresWrote 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/gaijinjoe/herdres/agents-md)<a href="https://agentmods.dev/instructions/gaijinjoe/herdres/agents-md"><img src="https://agentmods.dev/badge/instructions/gaijinjoe/herdres/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 5.1 | $0.02791 | $0.02791 |
| Opus 5 | $0.01396 | $0.01396 |
| Sonnet 5 | $0.00558 | $0.00558 |
| Haiku 4.5 | $0.00279 | $0.00279 |
Grade A, and why
herdres AGENTS.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 7d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (Devin, Codex, Claude, etc.) working in this repository.
What Herdres is
Herdres is a stdlib-only Python 3.11+ bridge that maps each Herdr space to a Telegram forum topic. It posts pane traffic into the mapped space topic, records the Telegram messages it sends as pane routing anchors, and lets an owner drive panes from Telegram (/send, /keys, plain-text replies, inline choice buttons, /new <agent> pane launches).
It does not patch Hermes or Herdr core. Routine sync uses no LLM calls. The cleanest mode (HERDR_TELEGRAM_TOPICS_TURN_FEED=1) consumes a structured herdr pane turn <id> --last --format json contract instead of parsing terminal text.
Operating vs contributing: this file guides agents working on herdres. To operate a deployment (install it, drive panes from Telegram), use the
skills/herdres/Agent Skill instead — it is the portable operator counterpart to this contributor guide.
Repository layout
| Path | Role |
|---|---|
herdres.py |
The main CLI. ~10k lines, single file, stdlib-only. Subcommands: sync, event, plugin-enable, plugin-disable, cleanup-duplicates, command, callback, managed-bot, probe. Owns the state file and the file lock. |
herdres_routing.py |
Pure routing/payload helpers (topic lookup, attachment extraction, command/callback payload builders). Shared by both gateways and the Hermes bridge. No I/O, no token. |
herdres_gateway.py |
Standalone inbound gateway for the managed-bots macOS path. Long-polls getUpdates per bot token (manager + each child bot), dispatches through a worker pool, embeds the Herdres command runner by default. |
herdres-gateway.py |
Simpler upstream/single-token gateway (Linux/no-managed-bots path). Imports herdres_routing. |
herdr_topic_bridge.py |
Async Hermes hook. Used when Hermes already long-polls the same bot token. Honors HERDRES_BRIDGE_DISABLED=1 to stand down when the standalone gateway owns inbound. |
herdr_turn_adapter.py |
Wrapper that adds herdr pane turn from agent session logs (Codex/Claude) when Herdr doesn't expose it yet. Delegates every other command to HERDR_REAL_BIN. |
herdres-plugin/herdr-plugin.toml |
Herdr 0.7.0+ plugin manifest: pane.agent_status_changed -> herdres event. |
install-user.sh |
Linux/systemd installer. |
install-macos.sh |
macOS installer: pins shebangs to a Python >= 3.11, installs launchd agents + the cockpit. |
launchd/, systemd/user/ |
Service/timer/plist templates (__HOME__ replaced by install-macos.sh). |
ssh/ |
Tailscale cockpit: ssh/server/ (Node.js, node-pty + ws, validates Telegram initData) and ssh/web/ (xterm.js Mini App). See ssh/README.md. |
tests/ |
pytest suite (456 tests). conftest.py loads the standalone scripts into sys.modules so tests can import herdres. |
.env.example |
All environment knobs with defaults and comments. The source of truth for config. |
assets/managed-bots/ |
Default JPG profile photos for managed child bots. |
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.
- 7d ago First seen · 128 lines · 2,791 tokens per session scan A 8863c4d625d9
herdres AGENTS.md is an instructions file published in the GitHub repository gaijinjoe/herdres (6 stars, last pushed 2mo ago), licensed MIT. It adds 2,791 tokens to every session, about $0.0140 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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).
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.