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/garudex-labs/caracal/command-architecturegit clone --depth 1 https://github.com/Garudex-Labs/caracalWrote 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/garudex-labs/caracal/command-architecture)<a href="https://agentmods.dev/instructions/garudex-labs/caracal/command-architecture"><img src="https://agentmods.dev/badge/instructions/garudex-labs/caracal/command-architecture.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 | $0.00342 | $0.00342 |
| Opus 5 | $0.00171 | $0.00171 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
caracal command-architecture.instructions.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.
What it actually says
Command Architecture
- Top-level
caracalruntime CLI commands must only manage local runtime lifecycle and setup: start, stop, status, purge, and optional interface launchers such asweb. - Top-level package scripts must not provide product-management aliases for zones, policies, grants, Control credentials, audit, agents, delegation, or other admin workflows.
- Product management must live only in the web console and its shared engine/admin helpers, with the Control API or Admin SDK for automation.
- The web console must expose product capabilities with consistent names, lifecycle behavior, terminology, and engine integration.
- The web console launcher (
caracal web) must remain optional; top-level help and dispatch must hide it when its workspace packages are unavailable. - If the web console is unavailable, the top-level runtime CLI must still expose lifecycle commands.
- Control API management is a web-console product-management surface; it must not be exposed as a top-level runtime command or recursively through remote Control dispatch.
- Runtime lifecycle code must not require admin tokens, zone selection, product credentials, or Control credentials.
- Command documentation must show runtime lifecycle examples through
caracaland product-management workflows through the web console (caracal web), the Control API, or the Admin SDK.
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 · 17 lines · 342 tokens per session scan A c141294b5736
caracal command-architecture.instructions.md is an instructions file published in the GitHub repository Garudex-Labs/caracal (205 stars, last pushed 5d ago), licensed Apache-2.0. It adds 342 tokens to every session, about $0.0017 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 2026-08-30.
Other instructions, from other repositories
emilia-protocol AGENTS.md
AGENTS.md instructions for emiliaprotocol/emilia-protocol, covering repository instructions for ai agents, required first read, source discipline, context maintenance and verification.
Doberman-Core AGENTS.md
AGENTS.md instructions for DobermanCore/Doberman-Core, covering claude.md — doberman operating manual, 0. on startup (every session), 1. what this repository is, 2. architecture & extension points and 3. prime directives (non-negotiable).
emilia-protocol CLAUDE.md
Claude Code instructions for emiliaprotocol/emilia-protocol, covering emilia protocol - repo guide, required context, critical, build & ship and outbound & claims.
emilia-protocol copilot-instructions.md
Copilot instructions for emiliaprotocol/emilia-protocol: Read AGENTS.md and AICONTEXT.md before proposing changes. Current evidence and provenance are in public/.well-known/emilia-context.json. Treat archived, staged, private, and outreach documents as non-authoritative for current behavior or standards status.
emilia-protocol GEMINI.md
Gemini CLI instructions for emiliaprotocol/emilia-protocol: Read AGENTS.md and AICONTEXT.md before analyzing or editing this repository. Use public/.well-known/emilia-context.json for current evidence counts and provenance. Do not infer current behavior or standards status from archived, staged, private, or randomly…
mcp-sso CLAUDE.md
Claude Code instructions for acartag7/mcp-sso, covering claude code session notes (mcp-sso) and repository quality rules.