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 skills add ojamin/okf-loom --skill okf-loomgit 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/skills/ojamin/okf-loom/okf-loom)<a href="https://agentmods.dev/skills/ojamin/okf-loom/okf-loom"><img src="https://agentmods.dev/badge/skills/ojamin/okf-loom/okf-loom/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ojamin/okf-loom/okf-loom"><img src="https://agentmods.dev/badge/skills/ojamin/okf-loom/okf-loom.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.02143 |
| Opus 5 | $0.00000 | $0.01071 |
| Sonnet 5 | $0.00000 | $0.00429 |
| Haiku 4.5 | $0.00000 | $0.00214 |
Grade A, and why
okf-loom 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 10d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okf-loom — repo-local skill
This repository is the skill. Clone it, load this SKILL.md, then use the
small resource files and checkout-local scripts referenced below. There is no
package-publishing workflow to learn; the durable artifact is this git repo
layout.
Default behaviours (do these without being asked)
These are the standing expectations for any agent using this skill:
- Docs are OKF bundles. When the user asks for documentation, notes, a
knowledge base, or "write this up", author it as OKF concepts — one
markdown file per concept with full frontmatter (
type,title,description,tags,timestamp, plusaliases/entities/relations/provenance/citationswhere they carry real information). Start a new bundle withscripts/okf-loom bootstrap <dir>or add to an existing one.docs-bundle/demo/showcase.mdis the canonical example of a fully-dressed concept (open it rendered to see why each key earns its place). - Validate after writing. Run
scripts/okf-loom validate <bundle>after any batch of writes and fix findings; runscripts/okf-loom discover <bundle>periodically to catch missing links/indexes/descriptions. In JSON discovery reports, act onactionability.safe_to_applyfirst, reviewneeds_review, and treat suppressed buckets as explanations unless the user asks for a broad audit. For imports or larger bundles, also runscripts/okf-loom graph-quality <bundle>as an advisory graph-health report (not a conformance gate). Ifindex.mdfiles are stale,scripts/okf-loom index <bundle>regenerates the generated blocks (marker-safe — it only rewrites betweenokf:generatedmarkers; hand-authored index prose without markers will be REPLACED, so checkgit diffafter). - Serve proactively. The rendered wiki is the product, not a debug view. Whenever the user wants to see, read, review, or comment on docs — or you have just built/changed a bundle they'd plausibly want to look at — start the studio without waiting to be asked and hand them the URL:
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.
- 10d ago First seen · 167 lines · 0 tokens per session scan A fbdbd59855ef
okf-loom is a skill published in the GitHub repository ojamin/okf-loom (7 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,143 tokens. 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 skills, from other repositories
policy-drift-audit
Run the policy/process drift audit. Surfaces stale, superseded, duplicate, non-canonical, and conflicting policy documents using DocGraph's built-in drift engine. Presents findings and optional remediation suggestions without writing governance decisions.
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
assessment-drift-audit
Run the assessment/research drift audit. Surfaces stale assessments, unverified evidence, competing interpretations, superseded research claims, and impacted deliverables using DocGraph's built-in drift engine. Presents findings and optional remediation suggestions without writing research decisions.
code-doc-drift-audit
Run the docs-code drift audit. Surfaces code files with no documentation references, broken doc-to-code links, and approved/review docs with no code anchors. Requires the codedoc domain pack to be enabled. Presents findings and optional remediation suggestions without writing code or governance decisions.
docgraph-drift-audit
Audit all .md files for DocGraph compatibility. Checks frontmatter, cross-references, heading structure, and wikilink conventions. Reports drift and suggests fixes.
documentation-standards
Use when writing README files, API documentation, user guides, or technical documentation following industry standards from Google, Microsoft, and GitLab style guides.