Write, review, debug and migrate Claude API code with model tables and a request linter built from live API probes of 15 models. Includes cost estimates and tested agent scaffolds.
An Agent Skill for writing, reviewing, debugging and migrating code that calls the Claude API.
What makes it different: its model tables and its request linter were built by sending 46 request
shapes to each of 15 Claude models and recording what the API accepted (see
references/request-rules.md). The linter's verdict matched the API on every recorded outcome.
Not affiliated with Anthropic. "Claude" is a trademark of Anthropic, PBC.
| Path | Purpose |
|---|---|
SKILL.md | When to use the skill, the working loop, the rules that cause most failures |
references/models.md | Ids, context, output caps, prices (generated) |
references/request-rules.md | What each model accepts, with exact error texts (generated) |
references/requests.md | Request anatomy, streaming, structured outputs, files, batches, token counting |
references/tools-and-agents.md | Tool definitions, the tool loop, server tools, agent architectures |
references/managed-agents.md | Core Managed Agents flow |
references/caching-and-context.md | Prompt caching, compaction, context editing, cost levers |
references/errors.md | Status codes and observed 400 messages with fixes |
scripts/claude-api.mjs | Offline CLI: models, lint, fix, migrate, cost, compare, scaffold, guide |
The scripts use only the Node.js standard library, open no network connection and need no key.
skills install @spboucher/claude-api-toolkit --client claude-code # or codex, cursor, generic-agent-skills
tests/skill-eval in the source repository asks a model to write Messages requests for specific
models, with and without this skill in its system prompt, and sends each result to the live API.
The measured acceptance rates are in CHANGELOG.md. It is a small evaluation (see the numbers and
their caveats there), not a benchmark.
A snapshot taken on the date in SKILL.md under API version 2026-10-21. Models the probing key
could not see are absent. Computer use, the advisor tool, memory stores, message threads and
cloud-platform differences were not probed. Cost output is an estimate. When the API and this
skill disagree, the API is right.
Destination: ~/.claude/skills/claude-api-toolkit · project scope: .claude/skills/claude-api-toolkit
1Install with the Skills CLI (verifies the checksum, previews the destination, never runs scripts)
skills install @spboucher/claude-api-toolkit@1.0.0 --client claude-codeAdd --project to install into .claude/skills/claude-api-toolkit instead of ~/.claude/skills/claude-api-toolkit.
2Or manually: download the release archive
curl -fsSLo claude-api-toolkit-1.0.0.tar.gz https://skills.spboucher.ai/api/v1/artifacts/spboucher/claude-api-toolkit/versions/1.0.0/download3Verify the SHA-256 checksum
echo "981f55265264f9b82ef013ea2d82c1490bb7d9476367c952335414603559cff3 claude-api-toolkit-1.0.0.tar.gz" | shasum -a 256 -c -4Inspect the contents before extracting
tar -tzf claude-api-toolkit-1.0.0.tar.gz5Extract into ~/.claude/skills/claude-api-toolkit
mkdir -p ~/.claude/skills/claude-api-toolkit && tar -xzf claude-api-toolkit-1.0.0.tar.gz -C ~/.claude/skills/claude-api-toolkitInstalling only copies or configures. Nothing is executed for you. The Skills CLI verifies the checksum before writing files.
Select a file to preview it. Files are shown as plain text and never executed.
No advisory findings from static-1.0.0 on Nov 10, 2026. 7 informational notes.
Static checks are advisory. They never certify that a package is safe. Compatibility entries are publisher claims unless marked verified.
| Version | Published | Size | SHA-256 | State |
|---|---|---|---|---|
| 1.0.0latest | Nov 10, 2026 | 35 kB | 981f55265264… | published |
Drive Safari on macOS with AppleScript: reliable page waits, reading, forms, uploads, downloads with the page's session, screenshots. Works in a dedicated window with domain policy and sensitive-field guards.
Write, review, debug and migrate OpenAI API code with model tables and a request linter built from live probes of 29 models. Covers Responses, Chat Completions, tools, costs and tested scaffolds.
Checks that every in-text citation in a Markdown or LaTeX manuscript has a bibliography entry, and the reverse.