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 scaccogatto/okf-skills --skill visualizegit clone --depth 1 https://github.com/scaccogatto/okf-skillsWrote 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/scaccogatto/okf-skills/visualize)<a href="https://agentmods.dev/skills/scaccogatto/okf-skills/visualize"><img src="https://agentmods.dev/badge/skills/scaccogatto/okf-skills/visualize/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/scaccogatto/okf-skills/visualize"><img src="https://agentmods.dev/badge/skills/scaccogatto/okf-skills/visualize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00111 | $0.00768 |
| Opus 5.5 | $0.00044 | $0.00307 |
| Sonnet 5.5 | $0.00022 | $0.00154 |
| Haiku 4.5 | $0.00011 | $0.00077 |
Grade A, and why
visualize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Visualize an OKF bundle
Generate a self-contained HTML graph of the target bundle. The bundle directory
is required, so pass .okf explicitly when no path is given. No backend, no
install, no bundle content leaves the page. The viewer does need network
access: cytoscape, marked and dompurify load from cdn.jsdelivr.net.
uv run "${CLAUDE_SKILL_DIR}/scripts/okf_visualize.py" $ARGUMENTS
If uv is unavailable:
python3 -m pip install --quiet pyyaml && \
python3 "${CLAUDE_SKILL_DIR}/scripts/okf_visualize.py" $ARGUMENTS
The detail panel shows each concept's type, description, tags, status,
generated, verified, stale_after, sources (with their credibility
signals, a usage_count alongside the usage_window that frames it), and
rendered body; a sources entry pointing at another concept in the bundle also
becomes a graph edge. A v0.1 timestamp is read as generated.at, so legacy
bundles still render fully.
Two badges are derived, not read: the §5.3 trust tier
(unverified / machine-confirmed / human-reviewed, keyed off the human:
prefix in verified[].by) and staleness (now >= stale_after). They are
advisory signals — when reporting on a bundle, say which tier a concept is in
rather than treating any of them as a gate.
| Flag | Effect |
|---|---|
-o <path> |
Output file (default <bundle>/viz.html). |
-t, --title |
Graph title (default parent/bundle dir name). |
-l, --link |
Source URL shown in the header. |
--layout |
cose, concentric, breadthfirst, circle, grid. |
--max-nodes N |
Exit 1 above N concepts (useful in CI). |
--og-image URL |
Absolute URL for the social preview image. |
Above 1,000 concepts the default switches to concentric (force freezes the
page; --layout cose overrides, and the in-page picker asks first). Above
5,000 it warns that the page loads slowly and reads as a hairball, and
suggests rendering a subdirectory.
Open it in any browser; ${CLAUDE_SKILL_DIR} resolves whether this runs as part
of the okf plugin or as a standalone skills.sh skill. The page is
deep-linkable: ?select=<concept-id> or #<concept-id> opens that concept,
?layout=<name> presets the layout.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed 7dea574f70a7
- 1mo ago Changed · +16 lines · +3 tokens per session 37a0a60d07d0
- 1mo ago First seen · 49 lines · 108 tokens per session scan A 2e79505c1fe4
visualize is a skill published in the GitHub repository scaccogatto/okf-skills (426 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 768 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
learn-from-correction
Propose a principle edit to a skill or persona file based on a (agentoutput, humanoutput) correction pair. Outputs a proposal markdown for human review - never auto-edits the target file.
research-mode
Anti-hallucination research mode. Toggle on to enforce citation requirements, source grounding, and "I don't know" behavior. Toggle off for creative work.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.
improve
Critique an outside idea (a pasted tip, post, transcript or video summary) against what this system already has. Use when the founder pastes something and asks whether to adopt it, or says 'improve', 'should we do this', 'compare this to what we have'. Grounded by scripts/improveground.py in the lessons corpora and…
fable-discipline
Engineering discipline distilled from a forensic read of one model's work. Use when building a feature, fixing a bug, writing tests, hardening a data path, or running any task that spans multiple files, sources, or sessions. Two layers: how to RUN the task (stage it, verify each stage with a check that can fail, write…
founder-voice
Founder voice enforcement for all written output. Apply to any text another person will read.