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/paultyng/skill-issue/verify-when-completenpx skills add paultyng/skill-issue --skill verify-when-completegit clone --depth 1 https://github.com/paultyng/skill-issueWrote 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/paultyng/skill-issue/verify-when-complete)<a href="https://agentmods.dev/skills/paultyng/skill-issue/verify-when-complete"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/verify-when-complete.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 | $0.00065 | $0.00771 |
| Opus 5 | $0.00032 | $0.00385 |
| Sonnet 5 | $0.00013 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
verify-when-complete 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 4d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify When Complete
No completion claims without fresh verification evidence.
This skill is the operational arm of ~/.claude/rules/probe-not-assume.md: claims of completion require fresh, probed evidence, not implementer self-report.
Core Principle
Evidence before claims, always. If you haven't run the verification command in this message, you cannot claim it passes.
Gate Rule
Before claiming any status or expressing satisfaction:
- Identify: What command proves this claim?
- Run: Execute the full command (fresh, complete)
- Read: Full output, check exit code, count failures
- Verify: Does output confirm the claim?
- If NO: state actual status with evidence
- If YES: state claim with evidence
- Only then: make the claim
Red Flags: Stop and Verify
- Using "should", "probably", "seems to"
- Expressing satisfaction before verification ("Great!", "Done!")
- About to commit/push/PR without verification
- Relying on a previous run, not a fresh one
- Trusting subagent success reports without independent verification
Detected Toolchain
!if [ -f Taskfile.yaml ]; then echo "taskfile"; elif [ -f Makefile ]; then echo "makefile"; else echo "raw"; fi
Use the detected toolchain above to select commands from the tables below.
Verification Steps
Run each step in order. If any step fails, stop and report the error.
Format
| Toolchain | Command |
|---|---|
| Taskfile | task fmt (if exists) |
| Makefile | make fmt (if exists) |
| Raw Go | go fmt ./... |
Lint
| Toolchain | Command |
|---|---|
| Taskfile | task lint (if exists) |
| Makefile | make lint (if exists) |
| Raw Go | go vet ./... |
Build
| Toolchain | Command |
|---|---|
| Taskfile | task build (if exists) |
| Makefile | make build (if exists) |
| Raw Go | go build ./... |
Test
| Toolchain | Command |
|---|---|
| Taskfile | task test (if exists) |
| Makefile | make test (if exists) |
| Raw Go | go test -race -count 1 -v ./... |
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.
- 4d ago First seen · 92 lines · 65 tokens per session scan A 9c8926175276
verify-when-complete is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 23d ago), licensed MIT. It adds 65 tokens to every session and 771 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 2026-08-31.
Other skills, from other repositories
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
expert
Base expert skill.
alpha
Alpha skill.
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.
codeql
CodeQL operational workflow — discover/config, run/inspect, triage SARIF findings (rule/query ID, source→sink, evidence), remediate, re-validate. Distinguishes broad MegaLinter linting from semantic security analysis.