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 TheGoat395/Codex-Skills --skill verification-before-completiongit clone --depth 1 https://github.com/TheGoat395/Codex-SkillsWrote 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/thegoat395/codex-skills/verification-before-completion)<a href="https://agentmods.dev/skills/thegoat395/codex-skills/verification-before-completion"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/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 5.1 | $0.00012 | $0.00502 |
| Opus 5 | $0.00006 | $0.00251 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
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 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.
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.
This is a copy
100% identical to verification-before-completion — 133 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Core principle
Evidence before claims. Verification should be fresh, decisive, and proportionate to the result being asserted. For an obvious low-impact local edit, apply the direct check without loading this skill or creating a formal verification artifact. Use this fuller workflow when the evidence choice, failure interpretation or completion boundary is nontrivial, or when explicitly invoked.
Lightweight gate
Before claiming that work is complete, fixed, passing, deployed, sent, published, or otherwise in a verified state:
- Name the exact claim and its consequence.
- Choose the smallest fresh check that can actually prove it.
- Run the check and read the exit status, failures, and material output.
- Report the result with exact coverage and anything not verified.
Do not replace a required runtime check with source inspection, a build with lint, or end-to-end evidence with an agent's success message. Do not run an entire test universe when a targeted regression plus the repository's required gate proves the claim.
Match evidence to the claim
| Claim | Decisive evidence |
|---|---|
| Targeted bug fixed | Reproduce the original symptom or run its regression test |
| Tests pass | The named test command exits successfully with zero relevant failures |
| Build succeeds | The actual build command exits successfully |
| Visual issue fixed | Inspect the rendered affected state at relevant viewports |
| Requirements met | Check each material acceptance criterion against code, output, or runtime evidence |
| External state changed | Read back the exact account, message, deployment, or service state |
| Research complete | State sources searched, semantic coverage, exclusions, and unresolved limits |
Coverage language
Use precise labels such as:
- source-inspected;
- structurally verified;
- targeted test passed;
- runtime-tested;
- visually inspected;
- external state confirmed;
- untested or blocked.
Never imply whole-system certification from a sample. Previous evidence may provide context, but a current completion claim needs current verification when the state could have changed.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -65 lines · -31 tokens per session 3d9d1ec205fc
- 4d ago First seen · 121 lines · 43 tokens per session scan A 2befe7fc55bc
verification-before-completion is a skill published in the GitHub repository TheGoat395/Codex-Skills (122 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 502 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to verification-before-completion, differing in 133 lines, and is treated as a copy.
Other skills, from other repositories
responsive-ui-qa
Inspect, diagnose, fix, and verify responsive frontend defects across routes, states, containers, and input modes. Use for mobile or desktop QA, overflow, overlap, broken navigation, unstable grids, clipped text, blank media, viewport regressions, screenshot comparison, and post-implementation visual verification.
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
copilotkit-agui
Use when building custom agent backends, implementing the AG-UI protocol, debugging streaming issues, or understanding how agents communicate with frontends. Covers event types, SSE transport, AbstractAgent/HttpAgent patterns, state synchronization, tool calls, and human-in-the-loop flows.
tdd
Test-Driven Development workflow for ALL Prowler components (UI, SDK, API). Trigger: ALWAYS when implementing features, fixing bugs, or refactoring - regardless of component. This is a MANDATORY workflow, not optional.
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.