cli: Skill for Claude Code

.claude/skills/schema-drift-fix/SKILL.md

schema-drift-fix is a skill for Claude Code from prolific-oss/cli. It costs 52 tokens per session (1,035 once invoked), scanned A, original, Apache-2.0.

A workflow for checking whether the Prolific CLI still matches the live Prolific API specification, the formal description of how the service works.

In plain words
What is it for?
Use it to investigate schema-drift issues or independently compare the CLI client with the current API contract.
Why use it?
It detects API drift, meaning the service and client code have become inconsistent, and drafts a fix for human review without committing or publishing it.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions AGENTS.md.

This is prolific-oss/cli's own configuration. It tells Claude Code how to work on cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to prolific-oss/cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/prolific-oss/cli/main/.claude/skills/schema-drift-fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/prolific-oss/cli

Made for: Claude Code.

Wrote 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.

agentmods badge for schema-drift-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/prolific-oss/cli/schema-drift-fix.svg)](https://agentmods.dev/skills/prolific-oss/cli/schema-drift-fix)
Your own site
<a href="https://agentmods.dev/skills/prolific-oss/cli/schema-drift-fix"><img src="https://agentmods.dev/badge/skills/prolific-oss/cli/schema-drift-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,035 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01035
Opus 5 $0.00026 $0.00517
Sonnet 5 $0.00010 $0.00207
Haiku 4.5 $0.00005 $0.00103

Measured 2d ago against content hash a41b7a27deee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

schema-drift-fix 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 2d 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.

.claude/skills/schema-drift-fix/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Schema Drift Fix

When to Use This Skill

Invoke this skill when the user:

  • References a schema-drift-labeled issue
  • Asks to "fix schema drift", "check for API drift", or similar
  • Uses the slash command /schema-drift-fix

Check whether the CLI's client package still matches the live Prolific API spec, and propose the fix if it doesn't — following the same checklist a human would use when adding a new API method. This skill investigates and drafts; it does not commit, push, or open a PR. The engineer reviews and does that themselves.

Arguments

issue-number (optional) — a schema-drift issue filed by .github/workflows/schema-drift-check.yml.

This skill does not depend on an issue existing. An issue is a convenient shortcut when CI already found and described drift, but the real source of truth is always a fresh go test ./contract_test/... run (Phase 1, step 1) — an issue's captured output can be stale by the time someone picks it up.

  • If issue-number is given: gh issue view <issue-number> --json title,body,state — confirm it's an open issue with a title matching API schema drift detected (...), and use its body as corroborating context.
  • If omitted: skip the issue lookup entirely and just run the check directly. This is the default, everyday way to invoke this skill — proactively, not only after CI has already filed something.

Phase 1: Investigate

  1. Run go test ./contract_test/... locally (this downloads the live Prolific OpenAPI spec itself, same as the workflow). If it passes: report "no drift detected" and stop here — there's nothing to do, regardless of whether an issue was given. If it fails, continue.
  2. If an issue number was given, cross-check its body against this fresh result — same operation(s) failing? Anything CI's snapshot called out that isn't reproducing now? Flag any mismatch rather than trusting either source silently.
  3. Identify which operation(s)/test case(s) are failing from the fresh output.
  4. Cross-reference contract_test/contract_test.go's operations table entry for the affected operation(s) against the live spec to determine exactly what changed (new/renamed/removed field, changed type, new required param, etc.).

Read the full file on GitHub · 80 lines

Changes

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.

  1. 2d ago First seen · 80 lines · 52 tokens per session scan A a41b7a27deee

Subscribe to this mod's changes

schema-drift-fix is a skill published in the GitHub repository prolific-oss/cli (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,035 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

platform-apex-generate

Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…

forcedotcom/sf-skills · 122 tokens

flow-next-impl-review

Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.

gmickel/flow-next · 34 tokens

flow-next-resolve-pr

Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.

gmickel/flow-next · 36 tokens

api-contract-review

Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.

TencentCloudBase/CloudBase-AI-Toolkit · 54 tokens

principle-model-the-domain

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.

cursor/plugins · 39 tokens

code-review-nodejs

Applies Node.js-specific code review patterns for async I/O, streams, security, process management, and dependency hygiene. Use when reviewing Node.js server code, route handlers, middleware, or any JavaScript file alongside package.json without TypeScript. Triggers on sync I/O in request paths, missing stream…

Jamie-BitFlight/claude_skills · 100 tokens