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/drvoss/everything-copilot-cli/verification-before-completionnpx skills add drvoss/everything-copilot-cli --skill verification-before-completiongit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWrote 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/drvoss/everything-copilot-cli/verification-before-completion)<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/verification-before-completion"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/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 | $0.00033 | $0.01889 |
| Opus 5 | $0.00016 | $0.00945 |
| Sonnet 5 | $0.00007 | $0.00378 |
| Haiku 4.5 | $0.00003 | $0.00189 |
Grade A, and why
verification-before-completion scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| API works | A real HTTP request such as `curl` | How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Do not claim a task is complete until you have fresh evidence from the command that proves the claim. Memory, prior runs, and "it should work" are not evidence.
When to Use
- Before saying a bug is fixed
- Before reporting that tests pass
- Before marking a PR ready for review
- Before saying "done", "resolved", or "working"
- When an agent sounds confident without showing current output
When NOT to Use
| Instead of verification-before-completion | Use |
|---|---|
| Exploring a hypothesis during debugging | systematic-debugging |
| Evaluating an LLM pipeline or agent output | eval-harness |
| Running the red/green cycle for a new feature | tdd-workflow |
Prerequisites
- You know the exact claim you want to make
- You know the command that would prove or falsify that claim
- You can inspect the full output and exit code
Pre-flight Plan Check
Before starting any task, validate the plan itself — not just after the work is done.
Ask:
- Does any step in the plan conflict with another (e.g., two steps that modify the same file in incompatible ways)?
- Does the plan match the stated objective, or has scope crept in?
- Are there hidden dependencies the plan does not account for?
Run the plan check before the first tool call, not after the work is in progress.
Pre-flight checklist:
[ ] Objective matches the actual request
[ ] No step conflicts with another
[ ] Scope matches what was authorized — no undeclared additions
[ ] Dependencies between steps are accounted for
If a conflict is found at pre-flight, resolve it with the user before proceeding. Fixing a wrong plan mid-execution costs more than catching it upfront.
Workflow
1. Identify the proving command
Ask: "What command would directly prove this claim right now?"
| Claim | Proving command |
|---|---|
| Tests pass | npm test -- --testPathPattern="<target>" or the project equivalent |
| Build succeeds | npm run build |
| Bug is fixed | The original reproduction command or failing test |
| API works | A real HTTP request such as curl |
| Migration succeeded | Direct state verification such as SELECT COUNT(*) ... |
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.
- yesterday First seen · 240 lines · 33 tokens per session scan A 1f0b46445135
verification-before-completion is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 1,889 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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
winui-design
Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…
winui-dev-workflow
Build and run workflow for WinUI 3 apps with WinApp CLI 0.6+ — project creation with winapp new, project-mode winapp run, BuildAndRun.ps1 analyzer integration, crash diagnosis, and prerequisites. Use when creating, building, running, or fixing build errors in a WinUI 3 project.
winui-packaging
MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…
winui-session-report
Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.
microsoft-build
Your companion for Microsoft Build 2026. Helps you find sessions relevant to your project, discover what's new for your tech stack, scaffold projects from sessions, and plan your event schedule. Activate when users mention sessions, schedule, what's new, Build, Ignite, AI Tour, Microsoft event, conference, or…
git-tidy
Comprehensive git repository hygiene in one pass: local and remote branches, worktrees, stashes, tags, remotes, merge and rebase artifacts, ignored-but-tracked files, large history blobs, and maintenance health. Every finding is classified by confidence (safe, review, keep) and nothing is deleted without explicit…