Borrowing it
Nothing to install: this file belongs to mfdaves/okf-mcp. 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/mfdaves/okf-mcp/main/.agents/skills/okf-v02-migration/SKILL.mdgit clone --depth 1 https://github.com/mfdaves/okf-mcpWrote 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/mfdaves/okf-mcp/okf-v02-migration)<a href="https://agentmods.dev/skills/mfdaves/okf-mcp/okf-v02-migration"><img src="https://agentmods.dev/badge/skills/mfdaves/okf-mcp/okf-v02-migration/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/mfdaves/okf-mcp/okf-v02-migration"><img src="https://agentmods.dev/badge/skills/mfdaves/okf-mcp/okf-v02-migration.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 | $0.00049 | $0.00687 |
| Opus 5 | $0.00024 | $0.00344 |
| Sonnet 5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
okf-v02-migration 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- okf-v02-migration — 91% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKF v0.2 Migration
Use the package's deterministic migration checker and proposal tools. Never rewrite catalog files directly, invent provenance or verification claims, accept proposals automatically, or mutate a remote bundle.
Workflow
- Confirm the repository worktree state before creating proposals. Preserve unrelated changes and stop if migration targets overlap unreviewed edits.
- Run
okf --root <catalog> migrate check. In an optional multi-root project, runokf --project <config> migrate check <bundle>. Record the classification, blockers, identity collisions, generated-file skips, referenced assets, and migration readiness. - Resolve blockers before proposing anything:
- Ask the catalog owner for a truthful
generated.byactor for every legacytimestamp; require an explicit confirmed mapping. - Route generated files back to their generator instead of proposing direct edits.
- Resolve malformed citations, conformance errors, unsafe paths, and ID or alias collisions without guessing.
- Supply mappings as
{"<concept-uri-or-path>":{"by":"<actor>","confirmed":true}};$defaultmay be used only after the owner confirms that one actor truthfully applies to every reported timestamp. - Use
human:<id>,process:<id>, or<provider>/<model>actor syntax. The checker rejects an omitted or non-boolean confirmation.
- Ask the catalog owner for a truthful
- Run
okf --root <catalog> migrate preview '<actor-mappings-json>', or supply the bundle id in multi-root project mode. Review every per-file change against field-mapping.md. - Present the preview and wait for explicit approval before calling
okf_propose_v02_migration. That MCP tool requires a writable local root and--authoring; there is intentionally no CLI command that creates proposals. - The proposal tool may create a migration manifest and individual child proposals only. Do not accept any child unless the user explicitly approves that proposal.
- Accept the reserved
index.mdversion proposal only after every Stage-A concept proposal is accepted and the whole bundle validates. - Run project validation again and report local evidence, retained legacy fields, remaining generator work, and any external or remote state not verified.
What ships with it
2 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.
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.
- 9d ago First seen · 38 lines · 49 tokens per session scan A 13dca6f2b4c4
okf-v02-migration is a skill published in the GitHub repository mfdaves/okf-mcp (6 stars, last pushed 27d ago), licensed MIT. It adds 49 tokens to every session and 687 once invoked, about $0.0002 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
okf-loom
Load this repo skill when working with Open Knowledge Format (OKF) bundles: validate, search, discover, update, render, serve the live studio, author concepts, or use the bundled OKF docs. The repo is the distribution unit; run scripts from the checkout with scripts/okf-loom.
christina
Unified Code Property Graph radar, sandboxed RLM execution, OKF semantic memory evolution, and swarm concurrency control.
christina-swarm
Swarm coordination: Kung-Robinson OCC concurrency, Tree-CRDT 3-way AST merge, and Linda tuple space.
christina-cpg
Code Property Graph AST radar: def-use chains, CFG, virtual interfaces, and blast radius analysis.
christina-memory
OKF semantic memory evolution: AGM belief revision, Ebbinghaus decay, and Mark-and-Sweep epistemic GC.
christina-rlm
Sandboxed RLM REPL execution with CoW rollback, 3-phase EGRI linting, and dynamic compute governor.