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/ferousco-dev/ilana/agents-mdgit clone --depth 1 https://github.com/Ferousco-dev/ilanaWhat 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 | $0.01735 | $0.01735 |
| Opus 5 | $0.00868 | $0.00868 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
ilana 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 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.
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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file has two audiences. Find yours.
- You were pointed at this repository and asked to install it. Read section 1, then stop.
- You are working on this repository as a contributor. Skip to section 2.
1. INSTALLING ÌLÀNÀ
Ìlànà is a software engineering process definition. It is documentation, shell and Python. It has no build step and no runtime dependencies.
What you are installing: the skill/ directory. Everything else in this repository is
scaffolding around it.
The install, in full
Run these. Substitute nothing.
git clone https://github.com/Ferousco-dev/ilana.git ~/.ilana-src
~/.ilana-src/bin/ilana install --link --all
~/.ilana-src/bin/ilana doctor
install --link --all creates symlinks from every coding-agent skills directory it finds on this
machine to ~/.ilana-src/skill. Because they are symlinks to one directory, a later
git -C ~/.ilana-src pull updates every agent at once.
doctor prints what it installed and where. Show the user that output. It is how they know it
worked.
About the ilana command
install --link --all already links the command into ~/.local/bin. If that directory is not on
the user's PATH, the installer says so and prints the exact line for their shell.
Relay that line to the user. Do not edit their shell profile yourself without asking.
Only ilana update, ilana doctor and the shell shortcuts need the command. The skill and the
slash commands work regardless, and the command always works by full path:
~/.ilana-src/bin/ilana doctor
To put it somewhere already on PATH: ILANA_BIN=/usr/local/bin ~/.ilana-src/bin/ilana install --link --all.
To skip it: add --no-cli.
If symlinks are not possible
Some sandboxes and some Windows setups will not follow them.
~/.ilana-src/bin/ilana install --copy --all
Updates then require ilana update rather than a bare git pull.
Installing for one project instead of the whole machine
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.
- 2d ago First seen · 187 lines · 1,735 tokens per session scan A 6b98abdb3d29
ilana AGENTS.md is an instructions file published in the GitHub repository Ferousco-dev/ilana (8 stars, last pushed 7d ago), licensed MIT. It adds 1,735 tokens to every session, about $0.0087 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 2026-08-31.
Other instructions, from other repositories
ultimate-seo-geo AGENTS.md
Instructions for mykpono/ultimate-seo-geo, covering ultimate seo + geo — llm-agnostic seo agent, 0. before you start, routing index, when not to run a full audit and audit context: internal vs. competitive.
ultimate-seo-geo copilot-instructions.md
Instructions for mykpono/ultimate-seo-geo, covering ultimate seo + geo — copilot instructions, how to use, key capabilities, quick start and reference files.
ultimate-seo-geo GEMINI.md
Instructions for mykpono/ultimate-seo-geo, covering ultimate seo + geo — gemini cli context, instructions, key commands, install dependencies first and run all individual checks.
mentor AGENTS.md
Instructions for ayhammouda/mentor, covering agents.md, what this is, repository structure, how the artifacts relate and validation.
workingclass AGENTS.md
AGENTS.md instructions for workingclass-ai/workingclass, covering repository agent instructions, how to use the skill and validation.
omg-payment-skill AGENTS.md
AGENTS.md instructions for chenmitchell/omg-payment-skill, covering agents.md — openai codex 與 agent sdk 使用指引, 適用對象, 載入方式, 方式一：作為知識庫 and 方式二：作為 system prompt extension.