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/ojamin/okf-loom/agents-mdgit clone --depth 1 https://github.com/ojamin/okf-loomWrote 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/ojamin/okf-loom/agents-md)<a href="https://agentmods.dev/instructions/ojamin/okf-loom/agents-md"><img src="https://agentmods.dev/badge/instructions/ojamin/okf-loom/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 | $0.00541 | $0.00541 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
okf-loom 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — okf-loom Skill
This repo is a loadable OKF skill checkout. Start with SKILL.md,
then load the focused resource file for the task you are doing.
Required orientation
- Read
SKILL.md— especially its Default behaviours: author docs as fully-dressed OKF concepts, validate after writing, serve the live studio proactively when the user wants to see or discuss docs (scripts/okf-loom serve <bundle> --no-open, add--tunnelfor a public link), and run the comment loop (wait→comment-claim→ mutators →comment-resolve) while a studio is up. - Use
scripts/okf-loom ...for runtime commands. - Use
docs-bundle/reference/spec.mdas the canonical current spec. - Do not reintroduce package publishing as the primary workflow. This git repo skill layout is the artifact.
What lives where
okf-loom/
├── SKILL.md # primary loadable skill entrypoint
├── resources/ # small agent-readable guidance files
├── scripts/okf-loom # checked-in helper command
├── scripts/okf_loom/ # checkout-local runtime package
├── docs-bundle/ # OKF docs bundle
├── samples/ # example bundles
├── tests/ # executable proofs
└── docs/ # screenshots, design plans (docs/design/)
Command baseline
scripts/okf-loom --help
scripts/okf-loom validate docs-bundle --strict
No primary runtime install step is required for normal docs validation. PyYAML is used when present; otherwise okf-loom uses its conservative built-in YAML fallback.
Hard rules
typeis the only hard-required concept frontmatter key in OKF v0.1.- Preserve unknown frontmatter keys and hand-authored content.
- Consumers tolerate broken links; mutators fail closed on missing targets
unless
--allow-forward-referenceis explicit. index.mdandlog.mdare reserved filenames.- Only the bundle-root
index.mdmay carry frontmatter. - Index regeneration must be marker-safe; log updates are append-only.
- All writes must stay atomic.
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.
- 4d ago First seen · 56 lines · 541 tokens per session scan A 4a0f5a9e34ed
okf-loom AGENTS.md is an instructions file published in the GitHub repository ojamin/okf-loom (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 541 tokens to every session, about $0.0027 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
DocGraph AGENTS.md
Instructions for Detective-XH/DocGraph, covering agents.md — docgraph fit guide for llm agents, the fit decision, decisive signals — any one means: use docgraph, supporting signals — useful when several hold together and anti-signals — prefer your own grep/read.
fieldtheory-cli CLAUDE.md
Instructions for afar1/fieldtheory-cli, covering claude.md, commands, architecture, key files and data flow.
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
abap_wiki AGENTS.md
AGENTS.md instructions for Gixsy95/abap_wiki, covering agents.md - abapwiki operating contract, 1. identity and mission, 2. language, 3. architecture: the two planes and 4. inviolable rules.
kiso copilot-instructions.md
Copilot instructions for oak-invest/kiso, covering kiso, project description, information, kiso features and design principles.