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.
npx agentmods add skills/madappgang/claude-code/verification-before-completionnpx skills add MadAppGang/claude-code --skill verification-before-completiongit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/madappgang/claude-code/verification-before-completion)<a href="https://agentmods.dev/skills/madappgang/claude-code/verification-before-completion"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/verification-before-completion.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 | $0.00031 | $0.01755 |
| Opus 5 | $0.00015 | $0.00877 |
| Sonnet 5 | $0.00006 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade B, and why
verification-before-completion scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
$ curl -X POST http://localhost:8000/users -d '{"email":"invalid"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| API changes | API test output or curl result | `curl -X POST ...` | Copies of this mod
1 near-identical copy found in the catalogue:
- verification-before-completion — 91% identical, 9 lines differ
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Iron Law: "NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE"
When to Use
This skill applies whenever you:
- Mark a todo item as complete
- Claim a bug is fixed
- Report a feature is ready
- State implementation is done
- Close a task or issue
- Prepare to commit changes
Red Flags (Violation Indicators)
- "should be done" / "should work now" (assumed completion)
- "probably works" / "likely fixed" (uncertainty without verification)
- "seems to work" / "appears correct" (observation without test)
- "Great!" / "Perfect!" / "All set!" (celebration without evidence)
- "I already tested this earlier" (stale evidence)
- Completion claim without test output shown
- Completion claim without grep verification for file changes
- Completion claim without screenshot for UI changes
- Completion claim without git diff for code changes
- Completion claim without build logs for configuration changes
- Completion claim without CI link for deployment changes
- "Just a small change, no need to verify" (size-based rationalization)
Key Concepts
Fresh Verification Principle
Verification must be fresh (performed after the claimed change) and explicit (evidence shown, not described).
Wrong:
Fixed the login bug in auth.ts. Should be working now.
Correct:
Fixed the login bug in auth.ts line 42:
git diff src/auth.ts:
- if (user.token == null) {
+ if (user.token === undefined || user.token === null) {
Test output:
✓ should reject undefined token (15ms)
✓ should reject null token (12ms)
✓ should accept valid token (8ms)
Evidence Types by Change Type
| Change Type | Required Evidence | Tool/Method |
|---|---|---|
| Logic/algorithm | Test output showing pass | bun test, pytest, go test |
| File creation | Grep verification or ls output | grep -r "pattern" . or ls -la path/ |
| UI/styling | Screenshot or video | Browser DevTools screenshot |
| Configuration | Build logs showing success | npm run build, cargo build |
| Deployment | CI link or deployment logs | GitHub Actions URL, kubectl logs |
| API changes | API test output or curl result | curl -X POST ... |
| Data migration | Row count or sample query | SELECT COUNT(*) FROM ... |
| Performance fix | Benchmark comparison (before/after) | hyperfine, go test -bench |
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.
- 2d ago First seen · 233 lines · 31 tokens per session scan B f4983dcd2332
verification-before-completion is a skill published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 1,755 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
github-evidence-kit
Generate, export, load, and verify forensic evidence from GitHub sources. Use when creating verifiable evidence objects from GitHub API, GH Archive, Wayback Machine, local git repositories, or security vendor reports. Handles evidence storage, querying, and re-verification against original sources.
fable-thinking
Reasoning protocol distilled from Claude Fable 5.1. Makes any model reason like Fable — evidence-grounded claims, multi-hypothesis diagnosis, concrete simulation, adversarial self-review, calibrated outcome-first delivery. Its never-skipped Floor check catches simple-looking trick questions models answer confidently…
verification-before-completion
Run verification commands and confirm output before claiming success.
PlanGate TDD Evidence Review
TDD を主張する実装の RED/GREEN/REFACTOR VERIFY 証跡（tdd-ledger）の妥当性を検査し、フェーズ順序・exitCode・test-cases との対応の欠落や偽装を検知する.
pm-verification-protocols
QA verification gate and evidence requirements.
verification-before-completion
Run verification commands and confirm output before claiming success.