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/code-stylegit 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/code-style)<a href="https://agentmods.dev/instructions/garudex-labs/caracal/code-style"><img src="https://agentmods.dev/badge/instructions/garudex-labs/caracal/code-style.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 | $0.00389 | $0.00389 |
| Opus 5 | $0.00195 | $0.00195 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
caracal code-style.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 4d 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
Code Style and Naming
- Applies to all source files across the entire codebase.
Required
- Use short, clear names for variables, functions, files, and folders.
- Use CamelCase as the default naming style.
- Use
_only when necessary (e.g., Python module files, test fixtures). - Match the naming pattern already in use in the surrounding code.
- Write comments as if the code is being read for the first time.
- Reuse and correct existing variables; update in place when possible.
- Keep the number of variables minimal and purposeful.
- Match the existing code's level of abstraction and style exactly.
Forbidden
- Must not use prefixes:
new_,fixed_,updated_,old_, or similar. Idiomatic Go constructors namedNewXare exempt. - Must not use
-in names. - Must not write comments referencing edits, history, or comparisons (e.g., "changed from", "updated to", "fixed", "previously", "now", "added", "removed").
- Must not reference prompt text, task descriptions, or requirements in comments.
- Must not write comments that restate what the code already expresses.
- Must not duplicate values into new variable names.
- Must not add abstractions, wrappers, or helpers for single-use operations.
- Must not add features, error handling, or logic beyond what was requested.
Commits
- Never add a co-author trailer for any AI agent or assistant to a commit (no
Co-authored-byline naming an AI tool, e.g. Copilot, Claude, Cursor, or any model/agent). Commits are attributed to the human author only.
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.
- 4d ago First seen · 33 lines · 389 tokens per session scan A d1f22e55bf79
caracal code-style.instructions.md is an instructions file published in the GitHub repository Garudex-Labs/caracal (205 stars, last pushed 4d ago), licensed Apache-2.0. It adds 389 tokens to every session, about $0.0019 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.
emilia-protocol CLAUDE.md
Claude Code instructions for emiliaprotocol/emilia-protocol, covering emilia protocol - repo guide, required context, critical, build & ship and outbound & claims.
Doberman-Core 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 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
Instructions for acartag7/mcp-sso, covering claude code session notes (mcp-sso) and repository quality rules.