verifying-completion

A checklist for proving that a coding task is finished with fresh evidence. It requires running the relevant verification command and reading its complete result before claiming success.

In plain words
What is it for?
Use it before marking a task done, approving a feature, declaring tests passed, or saying a fix is ready.
Why use it?
It prevents developers from saying that something works based only on assumptions, earlier runs, or code that appears correct. Failed checks must be reported as failures rather than treated as complete.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/acendas/shipyard/verifying-completion
Any agent
npx skills add Acendas/shipyard --skill verifying-completion
Clone the repo
git clone --depth 1 https://github.com/Acendas/shipyard

Made for: Claude Code, Codex.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.01588
Opus 5 $0.00006 $0.00794
Sonnet 5 $0.00003 $0.00318
Haiku 4.5 $0.00001 $0.00159

Measured 2d ago against content hash ecd4abacb656, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verifying-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 2d 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.

plugins/shipyard/skills/verifying-completion/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifying Completion

A task is "done" only when its acceptance is observable — right now, in this turn, with output you read. Internal confidence, prior runs, and "it should work" are not evidence.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

No completion claim is permitted unless the verification command ran in this message. Period.

Violating the letter of this rule is violating the spirit of this rule.

The Gate Function

Before flipping a task to done, marking a sprint complete, approving a feature, or asserting any "X works" / "tests pass" / "fixed" / "ready" — run this gate:

1. IDENTIFY: What command, in this exact moment, proves the claim?
2. RUN:      Execute the FULL command from a clean state (fresh shell, fresh build).
3. READ:     Read the FULL output. Capture exit code. Count failures.
4. VERIFY:   Does the output literally confirm the claim?
                YES → state the claim WITH the evidence inline (last 10 lines + exit).
                NO  → state actual status with the evidence; do NOT claim done.
5. ONLY THEN: Make the claim or flip the marker.

Skipping any step = lying, not verifying.

Claim → Evidence Map

Claim Required evidence Insufficient
Tests pass Test command output: 0 failed, exit 0, run in this turn "Last run was green" / "should pass"
Fix works Acceptance probe exit 0 with observable output proving wiring "Code looks right" / "compile clean"
Bug fixed The original failing test or repro now passes; ran in this turn "Code changed; assumed fixed"
Build succeeds Build command exit 0 in this turn Linter passing / "no syntax errors"
Linter clean Lint command output: 0 errors in this turn Partial check / extrapolation
Regression test added Red→Green→Revert→Red→Restore→Green cycle observed "Test passes once"
Subagent completed task Subagent's structured return AND git log shows commit AND probe ran Subagent reply alone
Acceptance scenario implemented Scenario maps to a passing test case AND the demo path runs end-to-end Code resembles the scenario
Sprint complete All tasks done AND full test suite passed in this turn AND review verdict captured Each task individually green at its own time
Spec compliance Each acceptance criterion has a probe/test result in this turn "Reviewer scanned the diff"

Read the full file on GitHub · 145 lines

Changes

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.

  1. 2d ago First seen · 145 lines · 13 tokens per session scan A ecd4abacb656

Subscribe to this mod's changes

verifying-completion is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 20d ago), licensed MIT. It adds 13 tokens to every session and 1,588 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

engenharia-de-requisitos

Use when doing requirements engineering, business analysis, or the software-engineering stage of discovering / specifying / validating / managing requirements — the stage BEFORE code (what to build) and AFTER (was the right thing built?), for new projects and for evolutions of existing ones. Triggers (EN)…

seekdevcore/sk-requirements-engineering-theskill · 0 tokens

engenharia-de-requisitos

Use when doing requirements engineering, business analysis, or the software-engineering stage of discovering / specifying / validating / managing requirements — the stage BEFORE code (what to build) and AFTER (was the right thing built?), for new projects and for evolutions of existing ones. Triggers (EN)…

seekdevcore/sk-requirements-engineering-theskill · 0 tokens

write-epic

Produces a complete epic definition following Atlassian agile guidance. An epic captures a large initiative that is too big for a single sprint and must be decomposed into user stories.

MarieLynneBlock/arcanum-artifex · 40 tokens

write-user-story

Produces a complete, ready-to-groom user story following the standard Atlassian/agile format. It applies the INVEST criteria and the 3 Cs framework (Card, Conversation, Confirmation) to ensure each story is well-scoped, valuable, and testable — not just syntactically correct.

MarieLynneBlock/arcanum-artifex · 64 tokens

rulesync

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.

dyoshikawa/rulesync · 64 tokens

agent-workspace-linux

Use when a task needs an isolated hidden Linux desktop or workspace-owned browser: GUI app QA, web/browser/shopping automation, sandboxed app observation, or stale workspace cleanup. Routes agent-workspace-linux MCP tools on demand. Does NOT apply to host desktop/Chrome control, generic MCP setup, or pure code/file…

ilysenko/codex-desktop-linux · 70 tokens