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 technicalpickles/pickled-claude-plugins --skill finding-api-docsgit clone --depth 1 https://github.com/technicalpickles/pickled-claude-pluginsWrote 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/technicalpickles/pickled-claude-plugins/finding-api-docs)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/finding-api-docs"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/finding-api-docs/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/technicalpickles/pickled-claude-plugins/finding-api-docs"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/finding-api-docs.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 | $0.01126 |
| Opus 5.5 | $0.00020 | $0.00450 |
| Sonnet 5.5 | $0.00010 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
api-documentation-discovery 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Documentation Discovery
Overview
When your training data conflicts with current API versions, STOP guessing and START discovering. This skill guides you to find current, accurate documentation using language-specific tools.
Core principle: Training data ages. Installed versions are truth. Use discovery tools to find what's actually there.
When to Use
Reactive Triggers (MUST use after these):
- ✅ 2+ failed attempts with same library/API
- ✅ Error patterns: "method not found", "wrong number of arguments", "unknown flag", "undefined method"
- ✅ Version mismatch symptoms in stack traces
Proactive Red Flags (STOP and check docs when you notice):
- ⚠️ You're confident about API usage but haven't verified current version
- ⚠️ User is confident but their syntax keeps failing
- ⚠️ You're making "one more tweak" to syntax
- ⚠️ You're using phrases like "should work", "likely correct", "probably just"
- ⚠️ You're pattern-matching from training data without verification
- ⚠️ You're about to claim something is "documented" without checking
When NOT to use:
- First attempt with clear error message pointing to fix
- Errors unrelated to API usage (logic bugs, type errors in your code)
The Discovery Workflow
Step 1: STOP Guessing
Recognize the trigger. Don't make another attempt based on patterns or user confidence.
Step 2: Identify Context
- What library/framework is failing? (check imports, stack traces, go.mod/Gemfile)
- What version is installed? (language tools show this)
- What operation are you trying? (the actual goal, not the syntax attempt)
Step 3: Use Language Discovery Tools
Check language-specific reference for HOW to discover documentation:
references/go.md- Go module explorationreferences/ruby.md- Ruby gem exploration
Follow progressive discovery: docs → examples → source
Step 4: Load Framework Reference (if available)
If framework-specific reference exists, load it for curated patterns:
references/go/cobra.md- Cobra CLI patternsreferences/ruby/rails.md- Rails patternsreferences/ruby/karafka.md- Karafka patterns
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 · 119 lines · 49 tokens per session scan A 668de6106a8d
api-documentation-discovery is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (11 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,126 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
create-pubsub-dotnet
This skill creates a Dapr pub/sub application in .NET — a publisher, a subscriber or both — with declarative (default), programmatic or streaming subscriptions, run with the Dapr CLI or .NET Aspire, using minimal APIs or controllers. Use this skill when the user asks to "create a pub/sub app in .NET", "build a Dapr…
create-pubsub-python
This skill creates a Dapr pub/sub application in Python with FastAPI — a publisher, a subscriber or both — with declarative (default), programmatic (dapr-ext-fastapi) or streaming subscriptions. Use this skill when the user asks to "create a pub/sub app in Python", "build a FastAPI publisher and subscriber with Dapr"…
create-workflow-from-diagram
This skill creates a Dapr workflow application from a diagram, scaffolded to run locally with the Dapr CLI (dapr run). Use this skill when the user provides a workflow image (PNG, JPG, JPEG, GIF, WebP) or a BPMN 2.0 XML file (.bpmn, .bpmn20.xml) and asks to "create a workflow from this diagram", "generate a Dapr…
create-workflow-typescript
This skill creates a Dapr application in TypeScript that runs locally with the Dapr CLI (dapr run) and demonstrates the core Dapr building blocks — Workflow, service invocation, pub/sub, bindings, jobs, state management, and secrets. Use this skill when the user asks to "create a workflow in TypeScript", "create a…
create-workflow-dotnet
This skill creates a Dapr workflow application in .NET that runs locally with the Dapr CLI (dapr run). Use this skill when the user asks to "create a workflow in .NET", "write a .NET workflow application" or "build a workflow app in C#". For a workflow that runs on Diagrid Catalyst, use the catalyst-ai plugin instead.
create-workflow-python
This skill creates a Dapr workflow application in Python that runs locally with the Dapr CLI (dapr run). Use this skill when the user asks to "create a workflow in Python", "write a Python workflow application" or "build a workflow app in Python". For a workflow that runs on Diagrid Catalyst, use the catalyst-ai…