llmoji AGENTS.md

Project instructions for llmoji, covering its agent workflow, processing pipeline, hook-installer abstraction, and synthesis backends.

In plain words
What is it for?
Use it as repository guidance when working on llmoji's agent hooks or synthesis pipeline.
Why use it?
The available excerpt contains no further details about the project or the tasks these instructions support.

Instructions file for CodexOpenCode

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/a9lim/llmoji/agents-md
Clone the repo
git clone --depth 1 https://github.com/a9lim/llmoji

Made for: Codex, OpenCode.

Per session 10,874 This file is loaded in full into every session.
When invoked 10,874 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.10874 $0.10874
Opus 5 $0.05437 $0.05437
Sonnet 5 $0.02175 $0.02175
Haiku 4.5 $0.01087 $0.01087

Measured 2d ago against content hash 19fe8205f075, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

llmoji AGENTS.md scanned grade B with 1 finding 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 2d 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.

1. Malformed `~/.claude/settings.json` — `_load_json_strict` raises
AGENTS.md · 858 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 2d ago First seen · 858 lines · 10,874 tokens per session scan B 19fe8205f075

Subscribe to this mod's changes

llmoji AGENTS.md is an instructions file published in the GitHub repository a9lim/llmoji (2 stars, last pushed 10d ago), licensed GPL-3.0. It adds 10,874 tokens to every session, about $0.0544 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.