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 DollarDill/beads-superpowers --skill verification-before-completiongit clone --depth 1 https://github.com/DollarDill/beads-superpowersWrote 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/dollardill/beads-superpowers/verification-before-completion)<a href="https://agentmods.dev/skills/dollardill/beads-superpowers/verification-before-completion"><img src="https://agentmods.dev/badge/skills/dollardill/beads-superpowers/verification-before-completion.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 73 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 78 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 84 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00043 | $0.01831 |
| Opus 5 | $0.00022 | $0.00915 |
| Sonnet 5 | $0.00009 | $0.00366 |
| Haiku 4.5 | $0.00004 | $0.00183 |
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 8d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Overview
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
The Gate Function
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence
5. ONLY THEN: Make the claim
6. CLOSE: If this verification gates a bead closure, run `bd close <id> --reason "description with evidence from step 4"`
Skip any step = lying, not verifying
Agent-Filed Bead Discipline
When a skill files a bead for discovered/follow-up work (not planned work), stamp it so a human can triage risk at a glance.
- Title: prefix
[spec]ONLY if speculative. Confirmed beads keep clean titles. - Body/notes — always include this 3-field stamp:
Severity: Critical | Important | Minor Confidence: Confirmed | Speculative Evidence: <file:line / failing test / repro> (or: none) - Mechanical rule: evidence cited →
Confidence: Confirmed; no evidence →Confidence: Speculative. Applies at all severities. Never blocks filing (surface-and-mark — Production-Grade Doctrine). - What counts as evidence (claim-substantiating AND checkable, not "a string exists"):
- ✅
parser.ts:142 — returns null on empty input (fails t_parse_empty) - ❌
parser.ts — looks wrong
- ✅
- High-severity nudge: a
Critical/Importantbead filed without evidence MUST add one line:Why this severity w/o evidence: <reason>. - Priority (
-p) stays human-owned — do not infer priority from severity. - Honest limit: this disciplines the instruction surface, not every runtime bead.
Confidence: Confirmedis a falsifiable triage hint that lowers verification cost, not proof. The convention is forward-only — pre-existing beads stay unstamped.
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.
- 8d ago First seen · 181 lines · 43 tokens per session scan A 6e11a2082159
verification-before-completion is a skill published in the GitHub repository DollarDill/beads-superpowers (26 stars, last pushed 17d ago), licensed MIT. It adds 43 tokens to every session and 1,831 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
goal-test
A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.
coverage-check
Run the repo's unit tests with coverage and verify that every file touched in the current change keeps line, branch, and function coverage at or above 95%. Language- and framework-agnostic. Use before committing, before PR creation, or when the user asks about coverage.
harness-validate
Use when user invokes /harness-validate or wants to check whether a harness.yaml file is valid according to the Harness Protocol v1 JSON Schema. Reports validation errors with field paths and helpful fix suggestions.
acceptance
A skill for writing, running, and repairing human-written acceptance checks stored in an `acceptance/ACCEPTANCE.md` file. Acceptance checks are executable tests of whether the finished result matches the requested outcome.