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/qingye-lab/rootloom/agents-mdgit clone --depth 1 https://github.com/qingye-lab/rootloomWhat 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 | $0.00297 | $0.00297 |
| Opus 5 | $0.00148 | $0.00148 |
| Sonnet 5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00030 | $0.00030 |
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.
What it actually says
Rootloom repository guidance
- Installable sources are
plugins/rootloom/for the four-entry Core andexperiments/rootloom-memory/for separately installed experimental Memory;.agents/plugins/marketplace.jsonmust point to those exact directories. maincontains Core plus optional Autonomy/Evidence; Project Memory is a separate optional plugin, and the unmaintained 1.2.19 branch is the Archived Assurance Edition. Seedocs/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.pywhen 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.mduser-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 checkonly when impact cannot be bounded, shared test-selection infrastructure changes, or an explicit repository or release gate requires it.
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 · 10 lines · 297 tokens per session scan A 773d32babb6e
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.
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.
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.
agents-reverse-engineer AGENTS.md
Instructions for GeoloeG-IsT/agents-reverse-engineer, covering agents-reverse-engineer, stack, subdirectories, architecture and behavioral contracts.
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.
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.
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.