incremental-validation

incremental-validation is a skill for Claude Code, Codex, Cursor from Rethunk-AI/clodbridge. It costs 19 tokens per session (1,696 once invoked), scanned A, original, MIT.

A coding practice of checking your work after each small change instead of waiting until a large feature is finished.

In plain words
What is it for?
It helps decide when to run type checks, tests, syntax checks, and integration tests during development.
Why use it?
It finds type errors, broken imports, and failing tests while the changes are still easy to understand and fix.

Skill for Claude CodeCodexCursor

Install

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.

agentmods
npx agentmods add skills/rethunk-ai/clodbridge/incremental-validation
Any agent
npx skills add Rethunk-AI/clodbridge --skill incremental-validation
Clone the repo
git clone --depth 1 https://github.com/Rethunk-AI/clodbridge

Made for: Claude Code, Codex, Cursor.

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 incremental-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/rethunk-ai/clodbridge/incremental-validation.svg)](https://agentmods.dev/skills/rethunk-ai/clodbridge/incremental-validation)
Your own site
<a href="https://agentmods.dev/skills/rethunk-ai/clodbridge/incremental-validation"><img src="https://agentmods.dev/badge/skills/rethunk-ai/clodbridge/incremental-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,696 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 $0.00019 $0.01696
Opus 5 $0.00010 $0.00848
Sonnet 5 $0.00004 $0.00339
Haiku 4.5 $0.00002 $0.00170

Measured 3d ago against content hash 39e8c1e291d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

incremental-validation 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 3d 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.

.cursor/skills/incremental-validation/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incremental Validation

The Golden Rule

Validate early and often. Find errors when they're small, not after you've written 1000 lines.

Validation Frequency Guideline

Milestone Validate? How Why
After writing 1 file (< 100 LOC) Optional Read for syntax Tiny files are easy to spot-check
After writing 2-3 files (100-300 LOC) YES tsc --noEmit Catch type errors before they cascade
After finishing a commit YES npm test Ensure behavior is correct
Before committing YES Both checks Never commit broken code
After a subsystem (5+ files) YES Integration test Verify systems work together

Validation Checklist

After writing code, before proceeding:

[ ] TypeScript compiles without errors
    npm run typecheck
    (Should output: 0 errors)

[ ] No syntax errors or import failures
    Read for obvious typos, unresolved imports

[ ] Tests pass (if you wrote tests)
    npm test
    (Should show: N passed, 0 failed)

[ ] All imports resolve
    No "Cannot find module" errors

[ ] No unused variables
    TypeScript strict mode catches these

Error Cascade Prevention

Scenario A: BAD (Validate After Everything)

Write types.ts (50 LOC)
Write parse.ts (150 LOC)
Write rules.ts (200 LOC)
Write skills.ts (100 LOC)
Write agents.ts (150 LOC)
    ↓ npm test
    ↓ 47 errors
    ↓ Spend 2 hours debugging
    ↓ Error was actually in types.ts

Problem: The error is hidden in a sea of code. Took 2 hours to find.

Scenario B: GOOD (Validate After Each File)

Write types.ts (50 LOC) → npm run typecheck ✓
    ↓ (commit)
Write parse.ts (150 LOC) → npm test ✓
    ↓ (commit)
Write rules.ts (200 LOC) → npm run typecheck ✓
    ↓ (commit)
Write skills.ts (100 LOC) → npm run typecheck ✓
    ↓ (commit)
Write agents.ts (150 LOC) → npm run typecheck ✓
    ↓ (commit)

Each validation takes 5-10 seconds.
Any error caught immediately.

Benefit: Errors caught in context. Fixed in 30 seconds instead of 2 hours.

Read the full file on GitHub · 283 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. 3d ago First seen · 283 lines · 19 tokens per session scan A 39e8c1e291d4

Subscribe to this mod's changes

incremental-validation is a skill published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 1,696 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.