Borrowing it
Nothing to install: this file belongs to chrisgleissner/llm-tools. 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/chrisgleissner/llm-tools/main/AGENTS.mdgit clone --depth 1 https://github.com/chrisgleissner/llm-toolsWrote 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/chrisgleissner/llm-tools/agents-md)<a href="https://agentmods.dev/instructions/chrisgleissner/llm-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/chrisgleissner/llm-tools/agents-md/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/chrisgleissner/llm-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/chrisgleissner/llm-tools/agents-md.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 | $0.12648 | $0.12648 |
| Opus 5.5 | $0.05059 | $0.05059 |
| Sonnet 5.5 | $0.02530 | $0.02530 |
| Haiku 4.5 | $0.01265 | $0.01265 |
Grade A, and why
llm-tools 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 yesterday.
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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Scope
This repo contains small Linux Python CLIs for Codex, Claude Code, GitHub Copilot, and Kilo Code CLI:
llm-usage— show local usage/quota for each provider, optionally through a local Unix-socket sampler service.llm-scheduler— submit a prompt to a provider CLI once usage data says it is usable (optionally waking/suspending around a scope reset).ralph-robin— keep using one configured provider until it is exhausted, then rotate to the next provider and delegate launch/suspend behavior tollm-scheduler. Holds an OS idle inhibitor for the whole run so a desktop idle timer cannot suspend the machine mid-work, and when every provider is rate-limited it sleeps the machine itself via a verified RTC wake (see Suspend/wake reliability below).llm-sleep-soak— repeatedly suspend and wake the machine using the exact production suspend path to prove sleep/resume is reliable on this hardware. Real-hardware test; cannot run in CI.llm-bridge— create durable local engineering missions, order tasks, inspect verification evidence, and supervise provider work through a terminal control station.llm_tools/common.py— shared helpers (provider readers, normalization, time/reset formatting, subprocess execution, usage decisions, PTY capture, wake diagnostics, and common CLI plumbing: argument validation, run-dir logging, prompt loading, argv/JSON conversion).llm_tools/bridge.py,bridge_store.py,bridge_runtime.py,bridge_monitor.py,bridge_sessions.py,bridge_logs.py,bridge_log_sink.py,bridge_refresh.py,bridge_tui.py, andterminal.py— Bridge CLI, private SQLite mission state, controller, bounded status projection, typed provider-session identity, bounded operation logs, asynchronous capacity observer and terminal UI, and isolated tmux station.llm_tools/usage_service.py— local-onlyllm-usagesampler service (Unix socket, latest snapshot, append-only history; systemd user service / launchd LaunchAgent install helpers).llm_tools/capacity.py— genericProviderId,CapacityKind,CapacityScope,ProviderSnapshot, andUsageDecisiondataclasses plus thedecide/validate_scope/scope_pacehelpers. All provider-specific reader code lives outside this module.llm_tools/providers/kilo.py— Kilo Code CLI adapter (parser forkilo stats --days <MTD>output, env-var fallback, command construction).llm_tools/providers/minimax.py— MiniMax adapter (parser formmx quota show --output jsonoutput, env-var fallback, command construction).- Python modules:
llm_tools/usage.py,llm_tools/scheduler.py,llm_tools/ralph_robin.py,llm_tools/sleep_soak.py,llm_tools/copilot_refresh.py, and package markerllm_tools/__init__.py. - Public direct-run command files:
llm-usage,llm-scheduler,ralph-robin,llm-sleep-soak,llm-bridge. - Regression tests:
tests/with pytest and fake provider commands. - Test helpers:
tests/conftest.py; main suites:tests/test_contracts.py,tests/test_additional_paths.py,tests/test_capacity.py,tests/test_kilo.py,tests/test_minimax.py,tests/test_ralph_kilo.py,tests/test_zai.py,tests/test_enabled_providers.py. - Project/package config:
pyproject.toml. - Import/test bootstrap:
sitecustomize.py. - CI:
.github/workflows/test.yml. - User docs:
README.md. - Local planning/work logs:
PLANS.md,WORKLOG.md. - Runtime data root:
${XDG_CACHE_HOME:-$HOME/.cache}/llm-tools, one subdirectory per tool. Legacy~/.cache/llm-usage,~/.cache/llm-scheduler, and~/.cache/ralph-robindirs are auto-migrated bymigrate_legacy_cache_dirsinllm_tools/common.py. - Usage cache and samples log:
${XDG_CACHE_HOME:-$HOME/.cache}/llm-tools/llm-usage(claude-status.json,claude-usage-api.json,llm-usage.log) - Usage service history/logs:
${XDG_CACHE_HOME:-$HOME/.cache}/llm-tools/llm-usage/service(latest.json,history.jsonl, service logs) - Usage service socket/pid:
${XDG_RUNTIME_DIR:-/tmp/llm-tools-$UID}(llm-usage.sock,llm-usage.pid) so Unix socket paths stay below platform length limits. - Copilot background refresh helper:
llm_tools/copilot_refresh.py, launched byread_copilotfor detached cache refreshes. - Bridge durable state:
${XDG_STATE_HOME:-$HOME/.local/state}/llm-tools/llm-bridge(overrideLLM_BRIDGE_STATE_DIR); SQLite mission/task/event/operation state, controller runtime files, verifier artifacts, and controller logs are stored below this private state directory. Provider-run logs are bounded by per-mission settings (default 4 MiB per file, three rotations, latest 20 run directories); pruned operation logs retain size and SHA-256 audit metadata. - Bridge tmux socket:
${XDG_RUNTIME_DIR}/llm-bridge/m-<mission-hash>.sockwhen a suitable private runtime directory is available, otherwise/tmp/lb-$UID/m-<mission-hash>.sock. This short private path avoids Unix socket length limits. No network listener is used. - Scheduler run logs:
${XDG_CACHE_HOME:-$HOME/.cache}/llm-tools/llm-scheduler/logs - Ralph Robin run logs:
${XDG_CACHE_HOME:-$HOME/.cache}/llm-tools/ralph-robin/logs - Ralph Robin state:
${XDG_CACHE_HOME:-$HOME/.cache}/llm-tools/ralph-robin/state.json - Suspend cycle ledger (durable, fsync'd; shared by ralph-robin and the soak):
${XDG_CACHE_HOME:-$HOME/.cache}/llm-tools/ralph-robin/suspend-ledger.jsonl - Sleep-soak run logs:
${XDG_CACHE_HOME:-$HOME/.cache}/llm-tools/llm-sleep-soak/logs
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.
- yesterday Changed · +9 lines · +537 tokens per session cda8bc5a89be
- 18d ago Changed · +2 lines · +83 tokens per session 65ba2df8bd65
- 26d ago Changed · +1 lines · +158 tokens per session 0988f00b8ec2
- 1mo ago First seen · 345 lines · 11,870 tokens per session scan A d624ca9d3ad6
llm-tools AGENTS.md is an instructions file published in the GitHub repository chrisgleissner/llm-tools (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 12,648 tokens to every session, about $0.0506 per session on Opus 5.5. 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
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core 10, parameterized queries, migration strategy.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.