agentmods.dev

cali AGENTS.md

Repository instructions for AI coding agents working on the Cali project. They explain how to identify the task, understand the repository layout, and use Cali’s shared runtime and command structure.

In plain words
What is it for?
Guiding code changes in the Cali CLI, its role modules, commands, shared runtime, tools, and related documentation.
Why use it?
They help an agent begin with the right files and contracts, reducing unnecessary exploration and inconsistent changes.

Instructions file for CodexOpenCode

990 2mo ago A scan 1,720 tokens original MIT
View the source file callstackincubator/cali
Install

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.

agentmods
npx agentmods add instructions/callstackincubator/cali/agents-md
Clone the repo
git clone --depth 1 https://github.com/callstackincubator/cali

Made for: Codex, OpenCode.

Per session 1,720 This file is loaded in full into every session.
When invoked 1,720 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01720 $0.01720
Opus 5 $0.00860 $0.00860
Sonnet 5 $0.00344 $0.00344
Haiku 4.5 $0.00172 $0.00172

Measured yesterday against content hash 6eca92bfa6f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cali 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.

AGENTS.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Minimal operating guide for AI coding agents in this repo.

First 60 Seconds

  • Classify the task:
    • Info-only: do not edit code or run checks unless needed.
    • Code change: make the smallest scoped edit and run the lightest relevant validation.
  • Read at most 4 files first:
    • the owning command module
    • one role module
    • one shared runtime file
    • one relevant doc file if the CLI or context contract changes
  • Define concrete success criteria before editing.
  • Prefer the shared runtime contracts over command-local improvisation.

Repo Shape

  • packages/cali: standalone CLI role platform
  • packages/tools: reusable Cali tools for other runtimes

Cali Runtime Shape

The cali package is now a small role platform.

  • CLI entry:
    • packages/cali/src/cli.ts
    • packages/cali/src/cli/app.ts
    • packages/cali/src/cli/*.ts
  • Command orchestration:
    • packages/cali/src/commands/*.ts
  • Shared runtime:
    • packages/cali/src/runtime/types.ts
    • packages/cali/src/runtime/context.ts
    • packages/cali/src/runtime/tool-packs.ts
    • packages/cali/src/runtime/tool-loop-role.ts
    • packages/cali/src/runtime/publishers.ts
    • packages/cali/src/runtime/mobile.ts
  • Config:
    • packages/cali/src/config/schema.ts
    • packages/cali/src/config/load.ts
  • Roles:
    • packages/cali/src/roles/*.ts
  • Tool packs:
    • packages/cali/src/tools/*.ts
  • Reports:
    • packages/cali/src/report/types.ts
    • packages/cali/src/report/render.ts
    • packages/cali/src/report/publishers/*.ts

Public Commands

Implemented first-class commands:

  • qa
  • review
  • perf-review
  • dev

Current maturity:

  • qa: ship-ready
  • review: experimental
  • perf-review: experimental
  • dev: experimental

publish is intentionally not implemented. Release automation belongs in CI or in dev-driven pipeline work, not as an open-ended agent command.

Core Contracts

Local Mode

Use --local android|ios for local mobile runs.

CI metadata is detected automatically in GitHub Actions and EAS. Use --ci github-actions|eas only when you need to override detection.

Read the full file on GitHub · 220 lines

Changes

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.

  1. yesterday First seen · 220 lines · 1,720 tokens per session scan A 6eca92bfa6f7

Subscribe to this mod's changes

cali AGENTS.md is an instructions file published in the GitHub repository callstackincubator/cali (990 stars, last pushed 2mo ago), licensed MIT. It adds 1,720 tokens to every session, about $0.0086 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.

Data and AIFrontendLLMWriting and docsagentsaireact-native
Related

Other instructions, from other repositories

evals AGENTS.md

Instructions for callstackincubator/evals, covering agents guide, what this repo is, mental model of execution, think-before-coding rules (required) and execution principles (default policy).

callstackincubator/evals · 1,309 tokens

agentic-mobile-blueprint AGENTS.md

Instructions for Ampli-Group/agentic-mobile-blueprint, covering agent context, task workflow, 1. check environment, 2. implement and 3. verify.

Ampli-Group/agentic-mobile-blueprint · 1,721 tokens

langgraph AGENTS.md

Instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.

langchain-ai/langgraph · 477 tokens

agentgateway copilot-instructions.md

Instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.

agentgateway/agentgateway · 41 tokens

hatch3r CLAUDE.md

Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).

hatch3r/hatch3r · 5,121 tokens

aeon CLAUDE.md

Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).

aeonfun/aeon · 3,720 tokens