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 skills add TechDufus/oh-my-claude --skill verificationgit clone --depth 1 https://github.com/TechDufus/oh-my-claudeWrote 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/techdufus/oh-my-claude/verification)<a href="https://agentmods.dev/skills/techdufus/oh-my-claude/verification"><img src="https://agentmods.dev/badge/skills/techdufus/oh-my-claude/verification.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 50 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 77 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 81 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00060 | $0.00974 |
| Opus 5 | $0.00030 | $0.00487 |
| Sonnet 5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
verification 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 8d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Skill
No evidence, no completion claim. Period.
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
"I think it works" is not evidence. "Tests passed 5 minutes ago" is not fresh. Run the checks NOW, read the output NOW, then claim completion.
When to Apply
- About to say "done", "complete", or "ready"
- Before committing or creating a PR
- After agent teammates claim work is finished
- When the
verification_reminderhook fires - Before any handoff to another person or system
Gate Function
IDENTIFY
What needs verification? List every claim you're about to make.
- Tests pass? Which test suite?
- Build succeeds? Which build command?
- Feature works? What specific behavior?
- No regressions? What could have broken?
RUN
Execute the actual checks. Not "I think they pass" - run them NOW.
- Run the test suite. Capture output.
- Run the build. Capture output.
- Run linters if applicable. Capture output.
READ
Read the output. Actually read it. Don't assume.
- Check exit codes (0 = success, anything else = failure)
- Look for warnings that might indicate issues
- Count passing vs failing tests
- Verify the output matches expectations
VERIFY
Does the output confirm success? Cross-reference against requirements.
- Every requirement has corresponding evidence
- No skipped tests that cover changed behavior
- No warnings that indicate degraded functionality
CLAIM
Only now can you claim completion. Include the evidence.
Common Failures
| Claim | Requires | Not Sufficient |
|---|---|---|
| "Tests pass" | Fresh test run output | "They passed before" |
| "Build succeeds" | Actual build output | "It should build" |
| "Feature works" | Demonstrated behavior | "I implemented it correctly" |
| "No regressions" | Full test suite run | "I only changed one file" |
| "PR is ready" | All checks green | "I think it's good" |
| "Bug is fixed" | Reproduction test passes | "I addressed the cause" |
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.
- 8d ago First seen · 114 lines · 60 tokens per session scan A 0ca47a2b8435
verification is a skill published in the GitHub repository TechDufus/oh-my-claude (176 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 974 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 2026-08-30.
Other skills, from other repositories
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.
taiyi-test
A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.
autoworker
Auto-loop execution workflow with quality gates. Use when starting any non-trivial implementation task. Provides automatic task decomposition, code implementation, testing (L1-L4), and iterative quality gates until completion. Invoke with /autoworker.
subtask-plan
Complete subtask verification plan: upstream traceability table + L1-L4 test plan + self-check. Call after autoworker:subtask-init. Makes subtask ready for code implementation.
subtask-update
Update subtask with fixes or new steps. Two trigger modes: (A) Auto-called by autoworker:gate-check on FAIL — reads FAIL info, adds supplementary steps. (B) User calls with a finding/bug during testing — diagnoses, fixes, updates subtask. Both modes end by invoking autoworker:dispatch to re-enter the loop.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.