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 agentmods add skills/cofin/flow/apilookupnpx skills add cofin/flow --skill apilookupgit clone --depth 1 https://github.com/cofin/flowWrote 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/cofin/flow/apilookup)<a href="https://agentmods.dev/skills/cofin/flow/apilookup"><img src="https://agentmods.dev/badge/skills/cofin/flow/apilookup.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.01079 |
| Opus 5 | $0.00023 | $0.00540 |
| Sonnet 5 | $0.00009 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
apilookup 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 3d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Lookup Skill
Look up API documentation, SDK references, library versions, and migration guides using a three-tier resolution strategy that starts with local Flow skill references and escalates to targeted web searches only when needed.
Overview
Three tiers of resolution, applied in order:
- Local skill references — if a matching Flow skill exists and the registry entry is fresh (< 30 days), load the skill's curated
references/docs directly. No network needed. - Targeted web lookup — if local refs are stale (> 30 days) or the query needs more, use the registry's known URLs for targeted searches (max 2-4).
- Arbitrary lookup — for technologies without a matching skill, broad web search with a version-first strategy (max 2-4 searches).
Usage Patterns
Example queries this skill handles:
- "What's the latest Litestar version and what changed?"
- "How do I use React Server Components?"
- "Show me the SQLAlchemy 2.0 migration guide"
- "What breaking changes are in Angular 19?"
- "What's the current Go module proxy API?" (arbitrary — no local skill)
- "Check if there's a newer version of Tailwind CSS"
How It Works
Version Registry
references/registry.json maps every Flow skill to:
- Current known version and last-checked date
- Package registry (PyPI, npm, crates.io, etc.)
- Official docs URL, changelog URL, and GitHub repo
- Search hint keywords for targeted queries
Staleness Thresholds
| Age of registry entry | Action |
|---|---|
| < 30 days | Trust local skill references, answer directly |
| 30-90 days | Use local refs as baseline, verify version via web |
| > 90 days | Treat as potentially outdated, do full version check |
Search Budget
All web lookups are capped at 2-4 searches max. Prefer WebFetch on known URLs over WebSearch when registry URLs are available — it is faster and more precise.
Lookup Rules
See references/lookup-strategy.md for the full decision tree. Key principles:
What ships with it
4 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.
- 3d ago First seen · 109 lines · 45 tokens per session scan A affe815ecc35
apilookup is a skill published in the GitHub repository cofin/flow (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,079 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 2026-08-30.
Other skills, from other repositories
write-documentation
Use when writing or substantially rewriting human-facing prose: documentation, README, guides, blog posts, emails, Slack messages, PR descriptions, release notes, or any text a human will read. Not for code comments, commit messages, or agent-to-agent communication.
document-release
Use when implementation on a branch is complete and it is about to be merged or PR'd — or when finishing-a-development-branch reaches its docs-audit gate — and after code changes are committed, to ensure all project documentation accurately reflects shipped code. Covers README, ARCHITECTURE, CONTRIBUTING, CHANGELOG…
stress-test
Use when a design, plan, or decision needs adversarial scrutiny before proceeding. Interrogates every branch of the decision tree, providing recommended answers and forcing explicit agreement or pushback. Triggers on "grill me", "stress test this", "poke holes", "challenge this design", or when…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.