Borrowing it
Nothing to install: this file belongs to gl00mt1t4n/loom-kg. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gl00mt1t4n/loom-kg/main/AGENTS.mdgit clone --depth 1 https://github.com/gl00mt1t4n/loom-kgWrote 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/gl00mt1t4n/loom-kg/agents-md)<a href="https://agentmods.dev/instructions/gl00mt1t4n/loom-kg/agents-md"><img src="https://agentmods.dev/badge/instructions/gl00mt1t4n/loom-kg/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 5.1 | $0.02482 | $0.02482 |
| Opus 5 | $0.01241 | $0.01241 |
| Sonnet 5 | $0.00496 | $0.00496 |
| Haiku 4.5 | $0.00248 | $0.00248 |
Grade C, and why
loom-kg AGENTS.md scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .git How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Use this when an agent is asked to initialize, customize, or maintain a LoomKG knowledge graph.
LoomKG is agent-agnostic. Hermes is recommended because it has native skills and persistent memory, but Claude Code, Codex, and other coding agents can follow this file too.
First response rule
When starting setup, do not explain between questions. Ask pointed questions back-to-back. Every question must include a default, and unanswered questions use the default. End with:
Answer the following questions one by one:
Setup questions
- What should this vault be called? Default:
<github-user>kg. - What local path should it live at? Default: the current cloned folder.
- What should the root index file be named? Default:
Root Index.md. - What GitHub username or organization should own the private knowledge graph repo? Default: the authenticated GitHub user.
- What should the private repo be named? Default:
<github-user>kg. - Should I keep this public starter as
template-upstream, or fully detach Git history and start fresh? Default: keep starter astemplate-upstream. - What primary domains do you want? Default:
Learning,Work,Systems,Decisions. - Should I include the support tags
workflow,system, andresearch? Default: yes. - Do you want a
Collegeor school domain? Default: no. - Do you want Hikari-knowledge or another external reference corpus? Default: no.
- Do you use Linear or another task system for actionable work? Default: no task system; document the boundary only.
- Should I install/update a global agent rule to consider knowledge/task capture after useful work? Default: yes, but only after detecting this agent's global instruction file, showing the exact destination/text, and getting confirmation.
- If Hermes is available, should I install the LoomKG skill into Hermes runtime skills? Default: yes.
- Should Obsidian be configured to show unsupported file extensions such as
.py? Default: yes. - After setup, should I create/push the private GitHub repo? Default: yes, private repo.
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.
- 8d ago First seen · 246 lines · 2,482 tokens per session scan C 9c8cde65969c
loom-kg AGENTS.md is an instructions file published in the GitHub repository gl00mt1t4n/loom-kg (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,482 tokens to every session, about $0.0124 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.