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 validategit 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/validate)<a href="https://agentmods.dev/skills/scaccogatto/okf-skills/validate"><img src="https://agentmods.dev/badge/skills/scaccogatto/okf-skills/validate.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 30 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00082 | $0.01015 |
| Opus 5 | $0.00041 | $0.00508 |
| Sonnet 5 | $0.00016 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
validate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate an OKF bundle
Run the deterministic conformance checker against the target bundle. Default to
the project's .okf/ directory when no path is given.
uv run "${CLAUDE_SKILL_DIR}/scripts/okf_validate.py" $ARGUMENTS
If uv is unavailable, fall back to:
python3 -m pip install --quiet pyyaml && \
python3 "${CLAUDE_SKILL_DIR}/scripts/okf_validate.py" $ARGUMENTS
${CLAUDE_SKILL_DIR} resolves whether this skill runs as part of the okf
plugin or is installed standalone (e.g. via npx skills add), so the checker is
always found alongside the skill.
Interpret the result:
- ERROR → a hard §11 conformance failure (no parseable frontmatter, a
missing/empty
type, or a file the checker cannot read as UTF-8). The bundle is non-conformant. Fix every one.
Only index.md and log.md are reserved: §11.1 makes every other .md in
the tree a concept, convention files included. An AGENTS.md or README.md
dropped next to a bundle is therefore an ERROR until it carries frontmatter with
a type (Document reads well), which is the fix; a skip-list would put the
checker out of conformance. Move the file above the bundle root if it is not
knowledge.
- warn → soft guidance (missing recommended field, non-ISO log date, broken
cross-link, a malformed v0.2 family, a footnote naming no source, an actor
that misses the §7 shapes, an Attested Computation missing
runtime, a computation path that resolves nowhere, frontmatter in a reserved file (§8, §9), a rootindex.mdcarrying extra keys or declaring a differentokf_version(§12)). Never blocks; broken links in particular are explicitly tolerated by the spec (§6.1). Fix when cheap.
One warning is worth more than the others: a §7 near-miss such as Human:dana
or human/dana. §5.3 keys trust tiers off the exact lowercase human: prefix,
so the concept silently reads as machine-confirmed when a person did review it.
Fix that one on sight.
v0.1 bundles validate too: a legacy timestamp or # Citations section is
reported as a warning naming its v0.2 replacement (generated.at, sources),
never as an error (§13.1). Under --strict those warnings do fail the run —
that is the migration nudge, and --migrate is the door.
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.
- 4d ago Changed · +10 lines 6544ba26a5fe
- 8d ago First seen · 76 lines · 82 tokens per session scan A 08a0a6951eeb
validate is a skill published in the GitHub repository scaccogatto/okf-skills (373 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 1,015 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
planning-with-scratchpad
Use when user explicitly requests planning with a scratchpad, or asks for persistent tracking of a complex task that the human can browse visually. Backs planning files with the scratch CLI so a pad's files are registered and viewable.
scratch
Organize knowledge from an agent session into a scratchpad — a folder of files plus a scratchpad.json manifest. Use when a task generates notes, snippets, command output, diagrams, or artifacts worth keeping together for a session/activity.
init
Initialize a personal Trove, a local file-based knowledge index for Claude Code. Use when the user says start/set up/create my trove, or when they want to remember things but no trove exists yet. Scaffolds the trove directory, INDEX.md and entries/ folder at user scope (/.claude/trove, follows you everywhere) or…
remember
Capture a durable learning into the personal Trove. Use when the user says remember this, note this, save to trove, add to my trove, or when a session surfaces a decision, gotcha, convention/preference, or external reference worth keeping. Writes one atomic entry file and updates INDEX.md.
query
Progressive retrieval from the Trove index. Use when the user asks what Trove knows about a subsystem, where code lives, or wants context assembled before editing. Runs architecture -> subsystem -> module -> symbol retrieval with a context budget.
index
Index the repository into Trove memory layers (symbols, modules, subsystems, architecture). Use when the user asks to index the repo, build the trove index, refresh symbols, or re-index after large changes.