rootloom AGENTS.md

A set of project instructions for the rootloom repository, a code project focused on making OpenAI Codex workflows inspectable.

In plain words
What is it for?
Use it when changing rootloom files, installation behavior, public contracts, user settings, documentation, or release material.
Why use it?
It records the repository’s rules for installation, documentation, compatibility, releases, and where different components belong.

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/qingye-lab/rootloom/agents-md
Clone the repo
git clone --depth 1 https://github.com/qingye-lab/rootloom

Made for: Codex, OpenCode.

Per session 297 This file is loaded in full into every session.
When invoked 297 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 $0.00297 $0.00297
Opus 5 $0.00148 $0.00148
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00030 $0.00030

Measured 2d ago against content hash 773d32babb6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rootloom 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 · 10 lines

What it actually says

Rootloom repository guidance

  • Installable sources are plugins/rootloom/ for the four-entry Core and experiments/rootloom-memory/ for separately installed experimental Memory; .agents/plugins/marketplace.json must point to those exact directories.
  • main contains Core plus optional Autonomy/Evidence; Project Memory is a separate optional plugin, and the unmaintained 1.2.19 branch is the Archived Assurance Edition. See docs/decisions/2026-07-29-rootloom-4-core-reset.md.
  • Component ownership and safety rules belong in the nearest nested AGENTS.md; keep this root file limited to constraints that apply across the repository.
  • Changes to installation, public behavior, contracts, or user configuration must update both English and Chinese documentation and extend scripts/validate_repo.py when an executable repository contract changes.
  • Baseline v2–v4 and Summary revision 5 are frozen compatibility formats; do not add Evidence formats, states, or schemas without a separately accepted product decision.
  • Release truth lives in GitHub PRs, Actions, tags, and Releases. Keep CHANGELOG.md user-observable, batch formal releases, and do not commit one-time plans or publication/final records.
  • Preserve unrelated work and default to impact-scoped checks. Use full make check only when impact cannot be bounded, shared test-selection infrastructure changes, or an explicit repository or release gate requires it.
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 · 10 lines · 297 tokens per session scan A 773d32babb6e

Subscribe to this mod's changes

rootloom AGENTS.md is an instructions file published in the GitHub repository qingye-lab/rootloom (7 stars, last pushed 20d ago), licensed MIT. It adds 297 tokens to every session, about $0.0015 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.

Related

Other instructions, from other repositories

ruleblast AGENTS.md

Instructions for Kpoiut/ruleblast, covering ruleblast repository instructions, evidence before confidence, change discipline and before a commit.

Kpoiut/ruleblast · 355 tokens

domain-experts CLAUDE.md

Instructions for wonsukchoi/domain-experts, covering domain experts — session bootstrap, non-negotiables when adding or editing roles, dual-graph context policy, mandatory: always follow this order and token usage.

wonsukchoi/domain-experts · 1,300 tokens

agents-reverse-engineer AGENTS.md

Instructions for GeoloeG-IsT/agents-reverse-engineer, covering agents-reverse-engineer, stack, subdirectories, architecture and behavioral contracts.

GeoloeG-IsT/agents-reverse-engineer · 4,955 tokens

karpathy-interaction-guidelines AGENTS.md

Instructions for hburaktasyurek/karpathy-interaction-guidelines, covering interaction guidelines, 1. think before acting, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

hburaktasyurek/karpathy-interaction-guidelines · 1,276 tokens

trellis AGENTS.md

Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.

craigcossairt/trellis · 3,686 tokens

ai-agent-instruction-modules AGENTS.md

Instructions for tablackburn/ai-agent-instruction-modules, covering ai agent instructions, instructions for ai agents, instruction applicability matrix, available instruction files and quick reference.

tablackburn/ai-agent-instruction-modules · 833 tokens