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 FradSer/dotclaude --skill verification-before-completiongit clone --depth 1 https://github.com/FradSer/dotclaudeWrote 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/fradser/dotclaude/verification-before-completion)<a href="https://agentmods.dev/skills/fradser/dotclaude/verification-before-completion"><img src="https://agentmods.dev/badge/skills/fradser/dotclaude/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/fradser/dotclaude/verification-before-completion"><img src="https://agentmods.dev/badge/skills/fradser/dotclaude/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 | $0.00060 | $0.00886 |
| Opus 5.5 | $0.00024 | $0.00354 |
| Sonnet 5.5 | $0.00012 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
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 22d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you have not run the verification command in this turn, you cannot claim it passes. The superpowers-evaluator reads narration and runs commands independently — your unverified "done" can be waved through unless it self-evidences.
Violating the letter of this rule is violating the spirit of this rule.
The Gate Function
Run this before claiming any status, expressing satisfaction, or returning a PASS-shaped verdict to the coordinator:
- IDENTIFY — What command proves this claim? (the task file's
## Verification Commands) - RUN — Execute the FULL command, fresh, in this turn. Not a previous run, not "should pass".
- READ — Full output, check exit code, count failures. Last 20-30 lines pasted into your return.
- VERIFY — Does the output confirm the claim?
- NO → state the actual status with evidence (exit code, failure count)
- YES → state the claim WITH evidence (exit 0, N/N pass)
- ONLY THEN make the claim.
Skipping any step is lying, not verifying.
Common Failures
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Original-symptom test passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Sub-agent completed | VCS diff shows changes + your re-run | Sub-agent reports "success" |
| Requirements met | Line-by-line checklist vs spec | Tests passing alone |
Red Flags — STOP
- Using "should", "probably", "seems to"
- Expressing satisfaction before verification ("Done!", "Great!", "Perfect!")
- About to commit, push, or return a PASS verdict without verification
- Trusting a sub-agent's success report without re-running verification yourself
- Relying on partial verification (only one of several test files)
- Thinking "just this once"
- ANY wording implying success without having run verification this turn
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.
- 22d ago First seen · 82 lines · 60 tokens per session scan A 045b91212b7a
verification-before-completion is a skill published in the GitHub repository FradSer/dotclaude (593 stars, last pushed 7d ago), licensed MIT. It adds 60 tokens to every session and 886 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.