verification-loop
Skill0 starsChanged 10 days agoMITView on GitHub
Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS/FAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.
84 other projects use a version of this, 66 of them edited.
Adopted by
Most recently taken up by
- Rojios/everything-claude-codeedited, first seen Nov 8, 2026
- lhbsaa/apex-unifiededited, first seen Nov 8, 2026
- shkodnik1917/claude-brainlabedited, first seen Nov 8, 2026
- pankaj-mahaur/Agent-Daemonedited, first seen Nov 6, 2026
- ek0212/agent-ready-repo-kittheir own version, first seen Nov 1, 2026
- TsinHzl/claude-code-configedited, first seen Nov 1, 2026
Used with
Projects with it also use everything-claude-code, everything-claude-code-conventions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
InfopibeSkilleverything-claude-code
Also in 10 projects that use this
mryeastcodeSkilleverything-claude-code-conventions
Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.
Also in 8 projects that use this
InfopibeSkillinvestor-materials
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
Also in 25 projects that use this
niloykumarbarmanSkillagent-sort
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
Also in 8 projects that use this
tpavanipradeepSkillnextjs-turbopack
Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
Also in 15 projects that use this
CodeWithBehnamSkilldmux-workflows
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
Also in 17 projects that use this
- +1 more from Infopibe
Other versions84 projects use a version of this.
Word for word · 0
None found.
Edited · 66
- affaan-m/ECC★ 246k80% same
- Galaxy-Dawn/claude-scholar★ 5.9k51% same
- xu-xiang/everything-claude-code-zh★ 1.9k17% same
- loulanyue/awesome-claude-notes★ 27283% same
- cloudnative-co/claude-code-starter-kit★ 15335% same
- cohen-liel/hivemind★ 10883% same
- tpavanipradeep/everything-claude-code★ 10483% same
- mturac/everything-openai-codex★ 8981% same
- mit-network/everything-claude-code★ 7683% same
- Fmarzochi/EGC★ 6181% same
56 more not listed
Wrote their own version · 18
- openJiuwen-ai/agent-core★ 464same name
- Resgrid/Core★ 238same name
- MRCalderon3D/everything-game-dev-code★ 105same name
- talayash/agentrium★ 48same name
- mhylle/claude-skills-collection★ 20same name
- Benkapner/claude-code-basecamp★ 17same name
- YehudaFrankel/clankbrain★ 16same name
- Yog-Sotho/claude-skills★ 4same name
- zhaoyii/my-skills★ 4same name
- peopleforrester/claude-dotfiles★ 3same name
8 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository39 other files it gives its agents.
- agent-architecture-auditSkill
- agent-evalSkill
- agent-harness-constructionSkill
- agent-introspection-debuggingSkill
- agent-security-hardeningSkill
- agent-self-evaluationSkill
- iterative-retrievalSkill
- prompt-optimizerSkill
- backend-patternsSkill
- database-migrationsSkill
- error-handlingSkill
- fastapi-patternsSkill
- postgres-patternsSkill
- redis-patternsSkill
- accessibilitySkill
- design-systemSkill
- frontend-patternsSkill
- react-performanceSkill
- docker-patternsSkill
- golang-testingSkill
- kubernetes-patternsSkill
- python-testingSkill
- react-testingSkill
- rust-testingSkill
- content-engineSkill
- market-researchSkill
- seoSkill
- api-designSkill
- brownfield-retrospectiveSkill
- codebase-onboardingSkill
- coding-standardsSkill
- context-budgetSkill
- continuous-learningSkill
- conventional-commit-reviewSkill
- orch-pipelineSkill
- plan-orchestrateSkill
- security-reviewSkill
- tdd-workflowSkill
- unified-memorySkill
The file
We split this skill into the rules it gives an agent
8 rules. 5 are common, 2 are distinctive, and 1 is very specific to this project.
5
Common
Most of the 78 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 16
After completing a feature or significant code change
- Common: line 17
Before creating a PR
- Common: line 18
When you want to ensure quality gates pass
- Common: line 32
If build fails, STOP and fix before continuing.
- Very specific: line 48
Use sed to limit displayed output while consuming the whole stream.
- Distinctive: line 99
When the requested outcome requires deployment or target-environment verification, report target acceptance separately from local checks.
- Distinctive: line 104
Do not access production or make external changes without authorization.
- Common: line 112
After running all phases, produce a verification report:
“Common” is measured: kept by at least 6 in 10 of the 78 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Verification Loop Skill
A comprehensive verification system for Claude Code sessions.
When to Use
Invoke this skill:
- After completing a feature or significant code change
- Before creating a PR
- When you want to ensure quality gates pass
- After refactoring
Verification Phases
Phase 1: Build Verification
set -o pipefail # report the build's exit status, not tail's
# Check if project builds
npm run build 2>&1 | tail -20
# OR
pnpm build 2>&1 | tail -20If build fails, STOP and fix before continuing.
Phase 2: Type Check
set -o pipefail
# TypeScript projects
npx --no-install tsc --noEmit 2>&1 | sed -n '1,30p'
# Python projects
pyright . 2>&1 | sed -n '1,30p'Report all type errors. Fix critical ones before continuing.
Phase 3: Lint Check
Use sed to limit displayed output while consuming the whole stream. This keeps a
successful linter from failing on SIGPIPE when pipefail is enabled.
set -o pipefail
# JavaScript/TypeScript
npm run lint 2>&1 | sed -n '1,30p'
# Python
ruff check . 2>&1 | sed -n '1,30p'Phase 4: Test Suite
set -o pipefail
# Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50
# Check coverage threshold
# Target: 80% minimumReport:
- Total tests: X
- Passed: X
- Failed: X
- Coverage: X%
Phase 5: Security Scan
# Check for secrets
grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
# Check for console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10Phase 6: Diff Review
# Show what changed
git diff --stat
git diff HEAD~1 --name-onlyReview each changed file for:
- Unintended changes
- Missing error handling
- Potential edge cases
Target Acceptance
When the requested outcome requires deployment or target-environment verification, report target acceptance separately from local checks. Record the environment and installed version when known, the evidence, and the next permitted check or precise access dependency. Passing local checks, review, merge, or release does not establish target acceptance. Report VERIFIED or FAILED for an executed target check, with its evidence. Do not access production or make external changes without authorization. For local-only tasks, mark target acceptance as not applicable.
For example: local checks PASS; staging verification NOT PERFORMED (no access); next step: an authorized maintainer runs the staging smoke test.
Output Format
After running all phases, produce a verification report:
VERIFICATION REPORT
==================
Build: [PASS/FAIL]
Types: [PASS/FAIL] (X errors)
Lint: [PASS/FAIL] (X warnings)
Tests: [PASS/FAIL] (X/Y passed, Z% coverage)
Security: [PASS/FAIL] (X issues)
Diff: [X files changed]
Overall: [READY/NOT READY] for PR
Target: [VERIFIED/FAILED/NOT PERFORMED/NOT APPLICABLE] (environment/version, evidence)
Next permitted step: [check or access dependency; none if complete/not applicable]
Issues to Fix:
1. ...
2. ...Continuous Mode
For long sessions, run verification every 15 minutes or after major changes:
Set a mental checkpoint:
- After completing each function
- After finishing a component
- Before moving to next task
Run: /verifyIntegration with Hooks
This skill complements PostToolUse hooks but provides deeper verification. Hooks catch issues immediately; this skill provides comprehensive review.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

