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 ArtemioPadilla/agent-triforce --skill verification-before-completiongit clone --depth 1 https://github.com/ArtemioPadilla/agent-triforceWrote 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/artemiopadilla/agent-triforce/verification-before-completion)<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/verification-before-completion"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/verification-before-completion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/verification-before-completion"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/verification-before-completion.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00586 |
| Opus 5 | $0.00022 | $0.00293 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
verification-before-completion 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Verify: $ARGUMENTS
The Rule
You MUST see evidence before claiming success. "It should work" is not evidence. A passing test run is evidence. A working command output is evidence.
When to Use
- Before claiming a bug is fixed
- Before claiming implementation is complete
- Before committing
- Before creating a PR
- Before telling the user "it's done"
- Before marking a task as completed
The Checklist
Before ANY completion claim, run through these:
-
Run the tests — see them pass with your own eyes
Run: {project test command} Expected: ALL tests pass Actual: {paste actual output} -
Verify the specific change — does it do what was requested?
Test: {specific verification for this change} Expected: {expected behavior} Actual: {paste actual output} -
Check for regressions — did you break anything else?
Run: {full test suite or broader test} Expected: No new failures Actual: {paste actual output} -
Verify the claim you're about to make — is it actually true?
- "Tests pass" — did you run them? did you see them pass?
- "Bug is fixed" — did you reproduce the bug, apply the fix, verify it's gone?
- "Feature works" — did you exercise the feature and see correct behavior?
Anti-Patterns
"It should work because..." Not evidence. Run it.
"I made the change so it will pass now" Not evidence. Run the tests.
"The logic is correct" Not evidence. See it work.
"I fixed the same kind of bug before" Not evidence for this bug. Verify this fix.
"Tests were passing before my change" They might not be now. Run them again.
Evidence Format
When reporting completion, include actual evidence:
Verification:
- Tests: {N} passing, {0} failing (command: {what you ran})
- Specific: {what you verified and what you saw}
- Regressions: none (full suite passing)
Integration with Agent Workflow
This skill reinforces the SIGN OUT checklist item "Stated build/test results (all passing, or documented what's failing and why)." The difference: this skill requires you to ACTUALLY RUN the verification and SHOW the output, not just state a claim.
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.
- 12d ago First seen · 87 lines · 43 tokens per session scan A 10f6607b8df3
verification-before-completion is a skill published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 586 once invoked, about $0.0002 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
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
reproducibility-validate
Run a workflow multiple times and compare outputs to produce a similarity score and pass/fail verdict.
eval-workflow
Run evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance.
execute-feedback
Execute tests on generated code and iterate until passing.
dos-witness-claim
Route subagent claims through independent read-back before another agent relies on them. Use at parallel, pipeline, or synthesis barriers where shipped phases, files, rows, messages, or other effects must be witnessed.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.