Borrowing it
Nothing to install: this file belongs to xiaohei-info/oh-my-multica. 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/xiaohei-info/oh-my-multica/main/AGENTS.mdgit clone --depth 1 https://github.com/xiaohei-info/oh-my-multicaWrote 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/xiaohei-info/oh-my-multica/agents-md)<a href="https://agentmods.dev/instructions/xiaohei-info/oh-my-multica/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaohei-info/oh-my-multica/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/xiaohei-info/oh-my-multica/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaohei-info/oh-my-multica/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 | $0.00817 | $0.00817 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
oh-my-multica 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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Repository Development Conventions
This file contains implementation guardrails specific to the oh-my-multica
(omac CLI) repository. Cross-project engineering practices are intentionally
omitted; only repository-specific, non-negotiable constraints belong here.
Hard Rules
The pipeline and CLI layers may call only the engines' WorkItemStore and
AgentRuntime interfaces. They must never shell out to platform CLIs directly.
Platform CLI calls (such as multica and gh) are encapsulated in engine
adapters. This rule allows future Linear or Jira integrations to add adapters
without changing the pipeline, and it is a code-review hard stop.
The web routing layer may only parse parameters, call command functions, and return JSON unchanged. It must not read manifests, call engines, or transform data. Humans, agents, and the web interface must always see the same facts.
Exit-Code Contract (§5.1 — Stable and Safe for Script Branching)
| Code | Meaning |
|---|---|
0 |
Success; every node in the DAG has converged to done. |
1 |
General error. |
2 |
Platform or network error. |
3 |
Authentication error, such as a platform CLI that is not signed in. |
5 |
Validation failure, such as lint or the evidence schema. |
10 |
Still advancing; used only by single-round tick mode. |
20 |
Caller decision required; includes a structured report. |
Business-layer OmacError subclasses map to their corresponding exit codes.
Do not scatter sys.exit calls. The exit-code contract must remain backward
compatible.
Terminology (§10.2 — Required in User-Facing Output and Documentation)
| Required term | Do not use |
|---|---|
result collection (collect_results) |
harvest |
running nodes (running_nodes) |
in-flight |
ready nodes (ready_nodes) |
frontier |
Use the required terms in identifiers, error messages, guide text, and design documents. Avoid ad hoc translated jargon.
TDD
- Write tests before implementation. New or changed executable behavior needs regression coverage. Cover at least the main path, boundaries, and known risks.
- Delivery = code + tests + necessary documentation. Changes to source
code, tests, build/package configuration, schemas, or executable behavior
require a green
python3 -m pytest tests/run for completion. - Use proportional verification for documentation-only changes. A diff
containing only Markdown or static diagram assets does not require the full
pytest suite. Run
git diff --check, verify local links and assets, and parse or render changed formats when tooling is available. If documentation is packaged or machine-consumed, run its relevant targeted tests. - Verify independently before completion. Writing code is not completion. Completion requires objective evidence from tests, builds, or actual command output.
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.
- 12d ago First seen · 81 lines · 817 tokens per session scan A 45460c5fb28d
oh-my-multica AGENTS.md is an instructions file published in the GitHub repository xiaohei-info/oh-my-multica (26 stars, last pushed 4d ago), licensed MIT. It adds 817 tokens to every session, about $0.0041 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).