limina AGENTS.md

Repository instructions for Limina, a research-focused runtime for autonomous technical investigation. They define how hypotheses, experiments, findings, durable notes, and review points should be organized.

In plain words
What is it for?
Managing Limina's active state, knowledge-base notes, research workflow, lessons, links, and validation checks after substantial edits.
Why use it?
They keep research work traceable and prevent unsupported experiments, findings, or scattered knowledge from accumulating.

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

Made for: Codex, OpenCode.

Per session 2,105 This file is loaded in full into every session.
When invoked 2,105 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 $0.02105 $0.02105
Opus 5 $0.01052 $0.01052
Sonnet 5 $0.00421 $0.00421
Haiku 4.5 $0.00211 $0.00211

Measured 2d ago against content hash bbf57f85c8b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

limina 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.

AGENTS.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Limina — Shared Runtime Contract

Limina is a research-first contract for autonomous technical investigation.

This file is the shared machine-facing instruction surface. Keep it short, specific, and stable. Runtime-specific details belong in adapters, skills, or scoped rules.

Core Rules

  1. Durable state lives in kb/. If it only exists in chat, it is not persistent.
  2. The only required core workflow is H -> E -> F.
  3. Do not create an experiment before the hypothesis exists.
  4. Do not create a finding before the experiment exists.
  5. ACTIVE.md is the only always-on state file. Keep it narrow.
  6. Keep files small and specific. Prefer a concrete artifact over a generic note.
  7. Store reusable lessons in kb/lessons/ as small topic files. Read only the ones you need.
  8. Use CR and SR only for real review points: major criticism, reset, or direction change.
  9. If the evaluation, baseline, or prior state looks untrustworthy, stop optimizing and resolve that first.
  10. Run python3 scripts/kb_validate.py after substantial kb edits and before closing kb-heavy work.
  11. Every note in the research core must include a ## Links section with real wikilinks.
  12. Artifact notes alias their ID in frontmatter, so use [[H001]], [[E003]], [[F010]], and similar links instead of raw file paths. Fixed notes use [[ACTIVE]], [[CHALLENGE]], and [[DASHBOARD]].

Mission First

Research exists to improve the mission, not to produce activity.

  • Optimize for decision-quality progress, not local artifact completion.
  • Treat benchmark or eval wins as mission progress only when the underlying capability is credible.
  • Prefer mechanisms that should generalize beyond the current slice, wording, customer, or benchmark.
  • If the current eval, baseline, or assumptions are not trustworthy, fix that before optimizing further.
  • If the problem changes, update the research graph to reflect the new reality instead of forcing continuity.

Working With The User

The user is the source of challenge framing, domain context, priorities, constraints, access, and missing information.

Read the full file on GitHub · 164 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. 2d ago First seen · 164 lines · 2,105 tokens per session scan A bbf57f85c8b9

Subscribe to this mod's changes

limina AGENTS.md is an instructions file published in the GitHub repository theam/limina (39 stars, last pushed 25d ago), licensed Apache-2.0. It adds 2,105 tokens to every session, about $0.0105 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.