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 Eilodon/DPS-Superskills-MCP --skill verification-before-completiongit clone --depth 1 https://github.com/Eilodon/DPS-Superskills-MCPWrote 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/eilodon/dps-superskills-mcp/verification-before-completion)<a href="https://agentmods.dev/skills/eilodon/dps-superskills-mcp/verification-before-completion"><img src="https://agentmods.dev/badge/skills/eilodon/dps-superskills-mcp/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/eilodon/dps-superskills-mcp/verification-before-completion"><img src="https://agentmods.dev/badge/skills/eilodon/dps-superskills-mcp/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 | $0.00038 | $0.02375 |
| Opus 5.5 | $0.00015 | $0.00950 |
| Sonnet 5.5 | $0.00008 | $0.00475 |
| Haiku 4.5 | $0.00004 | $0.00237 |
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 2mo 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Register: DISCIPLINE — Iron Law applies. Non-negotiable.
Core principle: Claiming work is complete without verification is dishonesty, not efficiency.
Violating the letter of this rule is violating its spirit.
The Iron Law
NO COMPLETION CLAIM WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
The Gate
BEFORE any success claim or completion statement:
1. IDENTIFY What command proves this claim?
2. RUN Execute fresh. Full output. Do not skip.
3. READ Full output. Exit code. Failure count.
4. ANCHOR Record: Evidence Anchor = command + result + timestamp
5. VERIFY Does output confirm the claim?
NO → state actual status with evidence
YES → state claim WITH evidence attached
6. CLAIM Only now make the claim
Skipping any step = lying, not verifying.
Evidence Tiers (VHEATM integration)
Not all evidence is equal. Label your evidence:
T1 — Direct observation this session (ran command, read output) → MANDATORY finding
T2 — External validation (CI passed, peer review confirmed) → REQUIRED finding
T3 — Indirect evidence (related test passed, pattern match) → MEDIUM confidence
T4 — Heuristic / inference ("should work", "looks correct") → NOT evidence
T4 is never evidence. Claims backed only by T4 are ASSUMED, not verified. Any completion claim requires T1 or T2.
Common Claims and What They Require
| Claim | Requires | Not Sufficient |
|---|---|---|
| "Tests pass" | Run test command → 0 failures (T1) | Previous run, "should pass" (T4) |
| "Bug fixed" | Test original symptom → passes (T1) + Fix Anchor | Code changed (T4) |
| "Linter clean" | Run linter → 0 errors (T1) | Partial check (T3) |
| "Build succeeds" | Run build → exit 0 (T1) | Linter passed (T3) |
| "Requirements met" | Line-by-line checklist (T1) | Tests passing (T3) |
| "Agent completed" | Inspect VCS diff → verify changes (T1) | Agent reports "success" (T4) |
| "Pattern globalized" | Grep run + results reviewed (T1) | "I checked similar code" (T4) |
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.
- 2mo ago First seen · 243 lines · 38 tokens per session scan A dfaffe7059dd
verification-before-completion is a skill published in the GitHub repository Eilodon/DPS-Superskills-MCP (0 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,375 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…