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 jscraik/Agent-Skills --skill oak-apigit clone --depth 1 https://github.com/jscraik/Agent-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/jscraik/agent-skills/oak-api)<a href="https://agentmods.dev/skills/jscraik/agent-skills/oak-api"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/oak-api/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/jscraik/agent-skills/oak-api"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/oak-api.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 | $0.00030 | $0.00658 |
| Opus 5.5 | $0.00012 | $0.00263 |
| Sonnet 5.5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
oak-api 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oak API
Philosophy
Learner safety, age fit, and compliance come before product cleverness.
When To Use
- The task depends on Oak API subjects, units, lessons, quizzes, search, or endpoint mapping.
- The user wants Oak content turned into a learner-facing flow or implementation plan.
- A child-facing app needs age fit, attribution, API-key handling, and rate-limit reminders.
Avoid
- Do not create generic educational content with no Oak data dependency.
- Do not dump Oak lesson material verbatim.
- Do not imply Oak endorsement or skip licensing and rate-limit reminders.
Inputs
- User request and target repo or artifact.
- Evidence source such as files, diffs, issues, releases, or existing workflow state.
- Any safety, privacy, compliance, or approval constraints.
Outputs
- Schema-bound outputs include
schema_version. - Age-appropriate learning flow or endpoint map.
- Compliance checklist and attribution.
- Implementation guidance when requested.
Workflow
- Collect age range, key stage, subject, learning goal, interaction style, and constraints.
- Confirm no learner PII and restore age/compliance context if the task drifts.
- Load only the archived Oak reference needed for the current request.
- Map content into explain -> practice -> check flows.
- Include required age, flow, compliance, attribution, pagination, and rate-limit markers when relevant.
- Use authenticated fetch tooling only when explicitly needed and keep keys in environment variables.
Constraints
- Redact secrets, API keys, and learner details by default.
- Use Oak endpoint claims only from archived references or live verified docs.
- Do not log credentials or imply Oak endorsement.
- Fail fast with
Missing inputs: age range, key stage, subject.when core context is absent.
Validation
- Run Plugin Eval and strict skill audit after editing this skill.
- Report exact validation commands and pass/fail outcomes.
- Fail fast: stop at the first failed gate, fix it, and rerun before continuing.
What ships with it
3 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.
- 1mo ago First seen · 74 lines · 30 tokens per session scan A 9cd49fdc616c
oak-api is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 658 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
agent-challenges
Agent skill for challenges - invoke with $agent-challenges.
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.
continuous-learning
Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.
note
Generate study notes from a lecture transcript and slides. Runs transcript + slide download in parallel, then writes a Markdown note with timeline outline.
trans
Transcribe a single Tongji Look lecture video to SRT + TXT, optionally download slide snapshots in parallel.
list
Discover and select courses from Tongji Look (look.tongji.edu.cn). Lists recent or all courses, filters by keyword, and saves the chosen course for use with /trans, /note, and other commands. Prerequisite for all lecture workflows.