Borrowing it
Nothing to install: this file belongs to VirtusLab/orca. 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/VirtusLab/orca/master/AGENTS.mdgit clone --depth 1 https://github.com/VirtusLab/orcaWrote 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/virtuslab/orca/agents-md)<a href="https://agentmods.dev/instructions/virtuslab/orca/agents-md"><img src="https://agentmods.dev/badge/instructions/virtuslab/orca/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/virtuslab/orca/agents-md"><img src="https://agentmods.dev/badge/instructions/virtuslab/orca/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 | $0.09896 | $0.09896 |
| Opus 5.5 | $0.03958 | $0.03958 |
| Sonnet 5.5 | $0.01979 | $0.01979 |
| Haiku 4.5 | $0.00990 | $0.00990 |
Grade B, and why
orca AGENTS.md scanned grade B with 2 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 14d 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.
| `<workDir>/.gemini/settings.json` | user tree | an `mcpServers.orca` entry for one interactive gemini turn | `GeminiSettings` | gemini | restored at turn end, and a stale entry from a crash dropped at the next interact Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
[`subprocess.QuietProc.call`](tools/src/main/scala/orca/subprocess/QuietProc.scala) How it starts
The opening of the file, as written. The whole thing — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Orca
Internals, architecture, and coding conventions for hacking on the library
itself. Build/test commands and the recipes for running a locally modified
orca live in CONTRIBUTING.md; end-user documentation at
orca.virtuslab.com (source in docs/).
Orca is implemented in Scala 3 on top of Ox for structured concurrency, tapir for JSON Schema derivation, and jsoniter-scala for codec generation.
Project layout
orca/
├── build.sbt / project/
├── tools/ # tool traits + os-backed impls (git/gh/fs), internal LLM SPI + session durability, InStage, events, subprocess
├── flow/ # stage/display/fail + FlowContext/FlowControl; orca.{plan,review,pr,progress}
├── claude/ codex/ gemini/ opencode/ pi/ # one module per coding-agent backend
├── runner/ # flow() entry, DefaultFlowContext/DefaultFlowControl, FlowLifecycle, terminal UI
└── shell/ # `orca-shell`, the `orca` CLI's interactive front-end (ADR 0021)
Dependency graph:
tools (standalone)
├── flow → tools
├── claude / codex / gemini /
│ opencode / pi → tools
├── runner → tools + flow + all five backends
└── shell → runner (published `orca`)
The runner module owns the flow entry point (package orca) and wires
defaults via DefaultFlowContext and DefaultFlowControl (package orca.runner); the stage
setup/teardown/recovery state machine is orca.runner.FlowLifecycle. The
terminal UI lives in orca.runner.terminal, behind an Interaction, so
swapping it for a Slack or HTTP equivalent is one substitution at the call
site rather than rewiring modules.
The user-facing surface lives in package orca (the flow entry, the tool
accessors — including planningAgent/codingAgent/reviewAgent, the
backend-agnostic role accessors (ADR 0020) — stage/display/fail,
JsonData, OrcaArgs and the RunTarget its flags parse into).
Implementations live in
focused subpackages: orca.tools (os-backed git/gh/fs impls + their traits),
orca.gitref (validated branch names and commit hashes, and Head),
orca.json (JsonData, RawJson, whole-file JsonFile documents),
orca.agents + orca.backend (LLM SPI, SessionSupport, per-backend
decoders; the SPI is private[orca] or private[backend], so a new harness
is added in orca itself), orca.subprocess (subprocess shim), orca.events
(event bus), one orca.backend.<backend> per coding agent, and orca.runner /
orca.runner.terminal (wiring + terminal UI). The flow module adds
orca.{plan,review,pr,progress}.
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.
- 14d ago Changed · +5 tokens per session cf0d908b01f2
- 23d ago Changed · +4 lines · +122 tokens per session ad2515bce96c
- 28d ago Changed · +5 lines · +20 tokens per session 5af0fcbb4da9
- 28d ago Changed · +12 lines · +151 tokens per session 953858b2b71b
- 1mo ago Changed · +11 tokens per session e019263d921b
- 1mo ago Changed · +32 tokens per session 2d303913fe9c
- 1mo ago Changed · +46 lines · +764 tokens per session 30a3d54f306a
- 1mo ago Changed · +72 lines · +1,985 tokens per session scan A → B a186bff3ff1f
- 1mo ago Changed · +8 lines · +161 tokens per session 5b8e786fa6ae
- 1mo ago First seen · 453 lines · 6,645 tokens per session scan A 6fcf21cc12a2
orca AGENTS.md is an instructions file published in the GitHub repository VirtusLab/orca (197 stars, last pushed 15d ago), licensed Apache-2.0. It adds 9,896 tokens to every session, about $0.0396 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
orca AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| orca AGENTS.mdVirtusLab/orca | Instructions file | 197 | 15d ago | Apache-2.0 | B | 9,896 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |