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 All-The-Vibes/ATV-Phoenix --skill phoenix-okfgit clone --depth 1 https://github.com/All-The-Vibes/ATV-PhoenixWrote 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/all-the-vibes/atv-phoenix/phoenix-okf)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-okf"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-okf/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/all-the-vibes/atv-phoenix/phoenix-okf"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-okf.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 | $0.00108 | $0.01085 |
| Opus 5 | $0.00054 | $0.00543 |
| Sonnet 5 | $0.00022 | $0.00217 |
| Haiku 4.5 | $0.00011 | $0.00109 |
Grade A, and why
phoenix-okf 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phoenix-okf — knowledge that pays rent in the open
Overview
OKF (Open Knowledge Format) is a vendor-neutral spec for
representing knowledge as a directory of markdown files with YAML frontmatter — one required key
(type), graph-shaped via plain markdown links, with index.md for progressive disclosure. It
is the format Phoenix's Context Assembly pillar already implies: pay once to understand
structure, then never again. This skill makes that knowledge portable and inspectable
instead of trapped in an opaque .token-master/graph.json.
A bundle is a directory. If you can
cata file you can read it; if you cangit cloneit you can ship it.
When to use
- You have a graphed repo (
.token-master/graph.json) and want the knowledge human-readable, diffable, and consumable by any tool (Obsidian, the OKF graph viewer, another agent). - You want skill discovery to ride a standard progressive-disclosure format.
- You want to feed an external OKF bundle (a data catalog, runbooks, org knowledge) into a Phoenix run as cheap context.
When NOT to use: a single local lookup grep answers in one turn. OKF earns its place on reusable, shareable knowledge, not one-off questions.
Three moves
1. Produce — code graph → OKF bundle
python scripts/okf_export.py --graph .token-master/graph.json --out okf-out --name <repo>
One concept document per source file; cross-file edges become bundle-relative markdown links.
INFERRED (name-matched, ~0.8-confidence) edges are flagged candidate — verify at the cited
file:line before trusting one for a risky change (phoenix-context honesty rule). Auto-writes
per-directory index.md, a root index.md (declaring okf_version), and a log.md.
2. Validate — the objective gate
python scripts/okf_validate.py okf-out
Checks OKF §9 conformance: every non-reserved .md has parseable frontmatter and a non-empty
type; reserved files (index.md/log.md) follow their rules. Exit 0 = conformant — use it as
a phoenix_sense check. Broken cross-links are tolerated per spec (warning, not error) unless
--strict-links.
What ships with it
10 files 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.
- checks/okf-conformant.json 126 B
- checks/okf-fresh.json 164 B
- checks/README.md 1.2 KB
- references/OKF-SPEC-0.1.md 15 KB
- scripts/okf_common.py 4.0 KB runs code
- scripts/okf_export.py 11 KB runs code
- scripts/okf_freshness.py 2.6 KB runs code
- scripts/okf_ingest.py 5.4 KB runs code
- scripts/okf_skillsync.py 3.6 KB runs code
- scripts/okf_validate.py 5.7 KB runs code
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.
- 11d ago First seen · 80 lines · 108 tokens per session scan A 7b8b3faed256
phoenix-okf is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 6d ago), licensed MIT. It adds 108 tokens to every session and 1,085 once invoked, about $0.0005 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 skills, from other repositories
paper-summarizer
Agents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PDFs, methodology review, limitations, practical implications, or extracting findings for engineering decisions.
upload-artifact
Upload a file as a ClosedLoop document (PRD, implementation plan, feature, or template). Reads file content and uploads via MCP without consuming conversation context. Also supports creating new versions of existing documents. Triggers on: "upload artifact", "upload PRD", "upload implementation plan", "upload…
extract-plan-md
Sync plan.md with plan.json content. MUST be used after ANY edit to plan.json to keep plan.md in sync. Triggers: After editing plan.json with Edit tool (REQUIRED - always sync after edits) User asks to "sync plan.md", "update plan.md", "extract the md from a plan" Converting plan.json to markdown or viewing plan as…
Presentations
Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.
Spreadsheets
Create, edit, analyze, and verify standalone spreadsheet files or Google Sheets-ready workbooks, including .xlsx, .xls, .csv, and .tsv. Do not use for live controlling Microsoft Excel app or a live Excel session.
template-creator
Create or update a reusable personal Codex artifact-template skill. Use when the user invokes $template-creator or asks in natural language to create a reusable template from a reference document, presentation, spreadsheet, ImageGen or Product Design image, email, or Slack message, or explicitly asks to edit or update…