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/raunakkathuria/operance/agents-mdgit clone --depth 1 https://github.com/raunakkathuria/operanceWrote 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/raunakkathuria/operance/agents-md)<a href="https://agentmods.dev/instructions/raunakkathuria/operance/agents-md"><img src="https://agentmods.dev/badge/instructions/raunakkathuria/operance/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 | $0.02353 | $0.02353 |
| Opus 5 | $0.01177 | $0.01177 |
| Sonnet 5 | $0.00471 | $0.00471 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
operance 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 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.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Source code lives under src/operance/. Keep portable core logic in modules such as models/, intent/, planner/, policy.py, validator.py, and executor.py. Platform readiness and setup policy belong in src/operance/platforms/; OS-native execution belongs in src/operance/adapters/, with mock.py used for developer-mode execution. Tests live in tests/unit/. Current product and milestone specs live in docs/specs/. Linux setup and integration details live in docs/requirements/. The initial implementation brief in docs/prompt/initial.md is historical context, not the current source of truth.
Build, Test, and Development Commands
Create and activate the local environment:
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install -e ".[dev]"
Run the full test suite with .venv/bin/python -m pytest. Run static checks with .venv/bin/python -m ruff check src tests scripts and .venv/bin/python -m mypy; both block in CI. Run the CLI locally with .venv/bin/python -m operance.cli --print-config or .venv/bin/python -m operance.cli --doctor. Use .venv/bin/python -m operance.cli --planner-request "open firefox" to inspect planner payloads during development, and .venv/bin/python -m operance.cli --planner-readiness "open firefox and notify me" to validate local planner health plus non-executing smoke before enabling live fallback.
Use stable lifecycle names for user-facing scripts. Do not add release-phase
names such as alpha, beta, or similar maturity labels to script filenames;
prefer names like scripts/setup.sh, scripts/run_fedora_gate.sh, or
scripts/run_release_readiness_gate.sh that remain valid across releases.
Coding Style & Naming Conventions
Target Python 3.12+. Use 4-space indentation, type hints, and small typed data models. Prefer snake_case for functions, modules, and variables, and PascalCase for classes and dataclasses. Keep platform-specific APIs out of portable core modules; expose them through adapter interfaces in src/operance/adapters/base.py. Match existing direct, minimal docstrings and avoid broad refactors in feature slices.
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 · 178 lines · 2,353 tokens per session scan A 29f55d25fe54
operance AGENTS.md is an instructions file published in the GitHub repository raunakkathuria/operance (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,353 tokens to every session, about $0.0118 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
chat-on-steroids CLAUDE.md
Claude Code instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
hex AGENTS.md
AGENTS.md instructions for anomalyco/hex, covering hex agent guide, purpose, feature map, architecture and invariants.
toks AGENTS.md
Instructions for Luzivog/toks, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
lite AGENTS.md
AGENTS.md instructions for ultralytics/lite, covering agents.md, core principles (critical), pr workflow, commands and architecture.
gnome-ui-mcp AGENTS.md
AGENTS.md instructions for asattelmaier/gnome-ui-mcp, covering agent guide, commands, rules for python and navigation workflow (preferred).
lite CLAUDE.md
Claude Code instructions for ultralytics/lite, a project described as: A fast, local workspace for Claude Code, Codex, Gemini CLI, Kimi Code, Qwen Code, DeepSeek, OpenRouter, and your shell.