Borrowing it
Nothing to install: this file belongs to Rethunk-AI/clodbridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rethunk-AI/clodbridge/main/.cursor/skills/verify-before-proceeding/SKILL.mdgit clone --depth 1 https://github.com/Rethunk-AI/clodbridgeWrote 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/rethunk-ai/clodbridge/verify-before-proceeding)<a href="https://agentmods.dev/skills/rethunk-ai/clodbridge/verify-before-proceeding"><img src="https://agentmods.dev/badge/skills/rethunk-ai/clodbridge/verify-before-proceeding.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 5.1 | $0.00023 | $0.01286 |
| Opus 5 | $0.00012 | $0.00643 |
| Sonnet 5 | $0.00005 | $0.00257 |
| Haiku 4.5 | $0.00002 | $0.00129 |
Grade A, and why
verify-before-proceeding 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 7d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Before Proceeding
The Golden Rule
Don't assume correctness. Verify every time you're about to move to the next feature.
Verification Checklist
After writing code, before committing:
Mandatory Checks
- TypeScript compiles —
npm run typecheckorbun run typecheck(zero errors) - No syntax errors — The parser can open the file
- Tests pass —
npm testif you wrote tests (100% pass rate) - Imports resolve — All
fromstatements find their targets - No unused variables — TypeScript strict mode catches these
Conditional Checks
- Integration test — If adding an MCP tool, call it and verify the response
- Glob matching test — If using micromatch, test with real file paths
- File fixtures exist — If parsing logic, do test files exist?
What to Do When Verification Fails
❌ DON'T
- Skip the failing check
- Assume it will work later
- Proceed to the next feature anyway
- Disable type checking or warnings
✅ DO
- Read the error message carefully
- Identify the root cause (typo, wrong import, logic error, missing file)
- Fix the code (or the test, if the test is wrong)
- Re-run verification
- Confirm it passes before proceeding
Common Errors and Fixes
Type Error: "Property 'globs' does not exist"
// Error: Property 'globs' does not exist on type 'RuleFrontmatter'
// Fix: Check types.ts — is 'globs' defined in the interface?
interface RuleFrontmatter {
description?: string;
globs?: string; // ← Add this if missing
}
Import Error: "Cannot find module './parse.js'"
// Error at src/reader/rules.ts:3
import { parseRuleFile } from './parse.js'; // Error
// Fix: Check that parse.ts exists in src/reader/
// If it exists, verify the import is using .js (for ESM)
Test Failure: "Expected ['src//.ts', '.md'], got ['src//*.ts ', ' *.md']"
// Bug: parseGlobs() is not trimming whitespace
// Fix:
function parseGlobs(raw: string) {
return raw
.split(',')
.map(s => s.trim()) // ← Add trim()
.filter(Boolean);
}
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.
- 7d ago First seen · 175 lines · 23 tokens per session scan A 19750a92e53e
verify-before-proceeding is a skill published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,286 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
api-aqa-flow
Workflow for backend API test automation: TMS / Issue Tracker test cases → automated API tests, HITL-gated.
testgen-flow
Workflow for generating test cases from requirements (Issue Tracker / Wiki sources), exporting to a Test Management System, etc.
ui-aqa-flow
Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.