Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Claudeloop Rest Surface

ASecurity

Explains the design of the generated `claudeloop api ...` command tree — introspecting the anthropic SDK's resource class tree, binding methods to Typer commands, the --raw/--stream/--provider modifiers, and the CI drift gate that enforces 1:1 parity with the SDK. Use this whenever building or modifying src/claudeloop/infrastructure/api/ (introspect.py, binder, gateway, providers) or the generated CLI sub-app, whenever the user asks about the REST API surface, the anthropic SDK's endpoints, o...

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentspythongoawsapi

Works with

cursorcliapi

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add the-vibey-project/vibey --skill claudeloop-rest-surface --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claudeloop Rest Surface?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Claudeloop Rest Surface
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/the-vibey-project-claudeloop-rest-surface/badge)](https://www.skillsdirectory.com/skills/the-vibey-project-claudeloop-rest-surface)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: claudeloop-rest-surface
description: Explains the design of the generated `claudeloop api ...` command tree — introspecting the anthropic SDK's resource class tree, binding methods to Typer commands, the --raw/--stream/--provider modifiers, and the CI drift gate that enforces 1:1 parity with the SDK. Use this whenever building or modifying src/claudeloop/infrastructure/api/ (introspect.py, binder, gateway, providers) or the generated CLI sub-app, whenever the user asks about the REST API surface, the anthropic SDK's endpoints, or "1:1 parity" / "drift gate" / "no gaps". Make sure to consult this before hand-writing any command under claudeloop api — every command in that namespace must be generated from SDK introspection, never hand-written one at a time, or the drift gate becomes meaningless and the "no gaps" claim becomes false.
---

# claudeloop REST surface (generated, not hand-written)


> **Codex skill mirror** of `.claude/skills/claudeloop-rest-surface/SKILL.md`. When this guidance changes, update Claude skill, Cursor rule, and `.agents/skills/` in the same PR.

`claudeloop api ...` covers all of the `anthropic` Python SDK's endpoint
methods without a single one being hand-written. This is the load-bearing
constraint of the whole subsystem — see ADR 0006 for why (short version:
Anthropic's own `ant` CLI already exists and covers this surface from the
same OpenAPI spec; a hand-written duplicate would silently rot the moment
anyone stopped tracking upstream SDK changes by hand).

## How discovery works — no live client needed

Walk the **class tree** under `anthropic.resources` via its
`cached_property` descriptors, not an instantiated `anthropic.Anthropic()`
client. This means discovery works with zero credentials configured — the
drift-gate CI test can run without any API key secret. Each leaf yields a
resource path, a method name, and its `inspect.signature`.

## Command binding rules

- **Path/scalar parameters** → real, typed Typer options.
- **Request body** → `--json <inline>` / `--json-file <path>` with `@path`
  file inlining, matching `ant`'s own approach — do not flatten every
  nested `TypedDict` field into individual flags; `ant` independently
  reached the same conclusion for the same reason (the request shapes are
  too deeply nested for that to stay usable).
- **`--raw`** selects the SDK's `with_raw_response` variant.
- **`--stream`** selects `with_streaming_response` where the method
  supports it.
- **`--max-items N`** bounds auto-pagination on list endpoints.
- **`--provider`** selects an alternate SDK client
  (`AnthropicAWS`/`AnthropicVertex`/`AnthropicBedrock`/
  `AnthropicBedrockMantle`/`AnthropicGoogleCloud`/`AnthropicFoundry`).
  **Only `AnthropicAWS`, `AnthropicGoogleCloud`, and `AnthropicFoundry`
  carry the SDK's full resource tree** — the others expose Messages and
  Beta only. The binder must reflect this per-provider difference; do not
  generate a command for a provider that would simply fail at runtime.

## The drift gate — what makes "no gaps" a real claim

A CI test enumerates every endpoint-backed method the installed `anthropic`
SDK exposes and asserts each has a registered `claudeloop api` command.
It also asserts the discovered method **count** against a committed
baseline, so a method disappearing from a newer SDK release is caught too,
not just additions. If you add a new hand-bound command (for one of the six
local helpers below), update the baseline deliberately — don't let the test
silently pass with a stale count.

## The six local helpers with no HTTP endpoint

`messages.stream`, `messages.parse`, `beta.messages.stream`,
`beta.messages.parse`, `beta.messages.tool_runner`, `beta.webhooks.unwrap`
— none of these map to a discoverable `cached_property` endpoint, so
introspection alone won't find them. Each must be **explicitly enumerated**
in the drift test as either hand-bound to a command or deliberately
exempted with a stated reason — never silently forgotten. If you're adding
support for one of these, add it to that explicit list, not just a new
Typer command.

## Full reference

`docs/architecture/decisions/0006-generated-rest-surface-not-hand-written.md`,
`docs/guides/rest-api-surface.md`.

Attribution

the-vibey-projectthe-vibey-project
View sourceSee grades on GitHubMore from the-vibey-project →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →