Home / robium-ai / robium · learnings/AGENTS.md · GitHub

AGENTS.md@learnings agentsA

AGENTS.md@learnings is agent-read markdown (agents) from robium-ai/robium.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Learning-engine guidance

This file applies under `learnings/` and to `scripts/engine/` work. Load the
`learning-loop` skill for consolidation, absorption, refining, experiments, or
retention maintenance.

## Capture without interrupting builds

- Hooks silently queue corrections/errors and archive session transcripts.
- Do not stop implementation to write a finding after every event. At a
  natural milestone, batch meaningful flags into `observations/<skill>.md` as
  `tentative` entries and discard context-free noise. A tentative entry needs
  only a status and a signal; consolidation completes it.
- A retro is useful only when it carries a real signal; clean per-skill score
  lines are not mandatory.
- Project-local facts belong in the owning app/site documentation, not in the
  cross-project learning corpus.

## Promotion and absorption

- Queue flags are pointers, not knowledge. Promote only when the transcript
  establishes expected behavior, actual behavior, and a skill or `new-skills`.
- Only `status: ready` observations can be absorbed. Preserve tentative,
  rejected, and absorbed entries as the dedup/audit trail.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add robium-ai/robium/learnings/AGENTS.md@git:20260922.d17aa3e
Exact content
mdr add robium-ai/robium/learnings/AGENTS.md@sha256:5fd9b0a27603ab5f

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_val57m4d2zbcohwg.svg)](https://markdownregistry.com/a/art_val57m4d2zbcohwg)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260922.d17aa3e latest2026-09-22 d17aa3e 2,656 BA view · diff
git:20260922.a4fc9b12026-09-22 a4fc9b1 2,526 BA view · diff
git:20260907.863840e2026-09-07 863840e 1,845 BA view · diff
git:20260828.a7b345e2026-08-28 a7b345e 1,780 BA view

Audit of the latest version

A  14 of 14 checks passed. Deterministic, no model, same answer every run.
  • pass: Size between 200 bytes and 200 KB (2656 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

robium-ai/robium · 14 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_val57m4d2zbcohwg
GET https://markdownregistry.com/api/v1/resolve?ref=robium-ai/robium/learnings/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/5fd9b0a27603ab5f7fc9a3e1531af9d923347572ec05f656da7f2173ea5456fc

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from robium-ai/robium

AGENTS.md agents
robium-ai/robium · AGENTS.md
git:20260907.863840e · audit A · 14 stars
CLAUDE.md claude
robium-ai/robium · CLAUDE.md
git:20260807.b408a93 · audit A · 14 stars
alpha skill
robium-ai/robium · cli/test/fixtures/skills/alpha/SKILL.md · A folded-scalar description that spans multiple indented lines and should be joined with single spaces. Second sentence…
git:20260907.863840e · audit A · 14 stars
beta skill
robium-ai/robium · cli/test/fixtures/skills/beta/SKILL.md · Plain single-line description.
git:20260907.863840e · audit B · 14 stars
CLAUDE.md@learnings claude
robium-ai/robium · learnings/CLAUDE.md
git:20260922.9c918e1 · audit B · 14 stars
AGENTS.md@skills agents
robium-ai/robium · skills/AGENTS.md
git:20260922.c5a4f3f · audit A · 14 stars
CLAUDE.md@skills claude
robium-ai/robium · skills/CLAUDE.md
git:20260922.9c918e1 · audit B · 14 stars
app-publishing skill
robium-ai/robium · skills/app-publishing/SKILL.md · Publish a tested Robium application as a coherent project page, article, and media set.
git:20260907.863840e · audit A · 14 stars
architect skill
robium-ai/robium · skills/architect/SKILL.md · Start robotics apps or demos from compatible examples for mapping/navigation, robot assistants, or pretrained…
git:20260919.498ea4e · audit A · 14 stars
cloud-run skill
robium-ai/robium · skills/cloud-run/SKILL.md · Deploy and debug headless robotics containers on Google Cloud Run.
git:20260907.863840e · audit A · 14 stars
data skill
robium-ai/robium · skills/data/SKILL.md · Choose and structure training data for robot-learning projects.
git:20260918.06c6019 · audit A · 14 stars
environments skill
robium-ai/robium · skills/environments/SKILL.md · Set up reproducible robotics environments with uv, Docker, or GPU hosts.
git:20260918.06c6019 · audit A · 14 stars

Every file in robium-ai/robium

Browse by kind, by grade A, or by owner.