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/nicolasmelo1/logion/agents-mdgit clone --depth 1 https://github.com/nicolasmelo1/logionWrote 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/nicolasmelo1/logion/agents-md)<a href="https://agentmods.dev/instructions/nicolasmelo1/logion/agents-md"><img src="https://agentmods.dev/badge/instructions/nicolasmelo1/logion/agents-md.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 | $0.01733 | $0.01733 |
| Opus 5 | $0.00866 | $0.00866 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
logion 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 3d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Orientation for AI coding assistants (Claude, Cursor, Aider, Codex, others) contributing to this repository.
If you are a human, CONTRIBUTING.md is the
authoritative document. This file is the AI-facing summary plus the
guardrails you will fail CI on if you ignore.
Protocol sources are mandatory
Before changing AI Catalog or ARD models, discovery APIs, catalog publication, identity, trust, attestations, federation, AKTP links, or related plans:
- read
protocol-specs/README.md; - read the applicable pinned normative specification and machine-readable
schemas under
protocol-specs/upstream/; - treat those sources as authoritative over plans, examples, comments, existing code, and model memory;
- keep AI Catalog representation, ARD discovery, native invocation, and AKTP evidence/improvement semantics separate;
- run
python3 scripts/check_protocol_specs.py.
If Logion conflicts with a pinned specification, do not improvise a hybrid. Document the conflict and either change Logion, review a newer upstream pin, or prepare an explicit upstream proposal.
What Logion is
Logion is an open-source resource-use, evidence, and improvement layer for AI agents. It indexes skills, plugins, MCP servers, models, and hosted Courses; integrates with native harness workflows; links consented use/feedback to exact versions; and coordinates reproducible improvement work. Commercial rails are optional sustainability infrastructure, not the project's primary identity.
This repository (logion/) holds the public developer surface:
packages/client/— Python SDKpackages/cli/— command-line interfacepackages/agent-companion/— first-party companion skill bundlepackages/landing/— public web scaffoldcontracts/openapi/v1.json— public API contractplans/andfuture-roadmap/— public planning projection and contribution surface
The backend that serves this contract is not in this checkout. Public planning is generated from the canonical maintainer source; see Guardrails below.
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.
- 3d ago First seen · 159 lines · 1,733 tokens per session scan A 576aeca0c9a8
logion AGENTS.md is an instructions file published in the GitHub repository nicolasmelo1/logion (35 stars, last pushed 5d ago), licensed MIT. It adds 1,733 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 2026-08-30.
Other instructions, from other repositories
hermes-agent-mt AGENTS.md
AGENTS.md instructions for cyborg-garden/hermes-agent-mt, covering hermes agent - development guide, what hermes is, contribution rubric — what we want / what we don't, what we want and what we don't want (rejected even when well-built).
hermes-bot-kit AGENTS.md
Instructions for thomasbek3/hermes-bot-kit, covering agent instructions for hermes bot kit, install the desktop plugins (default), verify the install, after installing — needs the human or a running app and optional: texting-style (agent plugin, per profile).
questionably-ultrathink CLAUDE.md
Claude Code instructions for snowmead/questionably-ultrathink, covering claude.md, development commands, validate plugin structure (run by ci), validate frontmatter syntax (run by ci) and directory structure.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
nocturnusai CLAUDE.md
Claude Code instructions for Auctalis/nocturnusai, covering claude.md, project overview, build & run commands, build all modules and run the http api server (port 9300).
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).