confidence-check

confidence-check is a skill for Claude Code from MichaelYcJo/SpecSeal. It costs 127 tokens per session (693 once invoked), scanned A, original, MIT.

A readiness check before implementation that tests whether the proposed work is understood and fits the project. It checks for existing solutions, architectural fit, current documentation, a working reference, and a known root cause or requirement.

In plain words
What is it for?
Use it before building a feature or fixing a bug. It helps decide whether to proceed, extend existing code, verify an API, find a proven example, or investigate further.
Why use it?
It catches duplicate work, incorrect APIs, unsupported approaches, and guessed bug causes before code is written. Any failed check is reported instead of being hidden by an overall score.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the specseal plugin — 23 skills, 3 agents, 3 hooks shipped together

Good fit Use it before building a feature or fixing a bug. It helps decide whether to proceed, extend existing code, verify an API, find a proven example, or investigate further.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/michaelycjo/specseal/confidence-check
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.

Any agent
npx skills add MichaelYcJo/SpecSeal --skill confidence-check
Clone the repo
git clone --depth 1 https://github.com/MichaelYcJo/SpecSeal

Made for: Claude Code.

Or install specseal, the plugin that ships this one along with the rest of its 23 skills, 3 agents, 3 hooks.

Wrote 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.

agentmods badge for confidence-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/michaelycjo/specseal/confidence-check/github.svg)](https://agentmods.dev/skills/michaelycjo/specseal/confidence-check)
Your own site
<a href="https://agentmods.dev/skills/michaelycjo/specseal/confidence-check"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/confidence-check/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.

agentmods 80×15 button for confidence-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/michaelycjo/specseal/confidence-check"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/confidence-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 693 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00127 $0.00693
Opus 5 $0.00063 $0.00347
Sonnet 5 $0.00025 $0.00139
Haiku 4.5 $0.00013 $0.00069

Measured 8d ago against content hash 70d18adcf0d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

confidence-check 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.

skills/confidence-check/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

confidence-check — is the ground under this actually known?

Three things get assumed at the start of implementation and are wrong often enough to be worth a minute: that nothing equivalent already exists, that the API is what you remember, and that the bug's cause is understood rather than guessed. Settle them before writing, not after.

Five checks

  1. No duplicate exists

    • Search codebase for similar functionality
    • Check if existing code can be extended instead
  2. Architecture compliant

    • Uses existing stack/patterns in the project
    • No unnecessary new dependencies
    • Follows project's established conventions
  3. Official docs reviewed

    • Library/framework API verified against current version
    • Breaking changes checked if upgrading
  4. Working reference found

    • OSS example or proven pattern identified
    • Not relying on untested approach
  5. Root cause understood

    • For bugs: clear understanding of WHY it fails
    • For features: clear understanding of requirements

What to do with the answers

Any check unsatisfied — say which, and ask. All five satisfied — proceed. That is the whole rule, and it is what the old weighted score already encoded: the weights summed to 85 without any one of them, so a single miss could never reach the "proceed" band. The percentage carried no information the list of failed checks did not, while looking like a measurement.

It also invited the wrong move. A number can be nudged — one check called "partial" instead of "failed" lifts the total past a threshold, and nothing in the report shows that happened. A named unsatisfied check cannot be nudged; it is either answered or still open.

An unsatisfied check is not a reason to stop. It is a thing to say out loud before writing code, so the person who can settle it gets the chance. Most are settled in one exchange.

Output format

Ready:      <checks satisfied, one line each>
Not ready:  <check> — <what is missing, and what would settle it>
Unknowable here: <check> — <who can answer>

<Proceeding / Asking first>, because <the one sentence that follows from above>.

Read the full file on GitHub · 80 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. 8d ago First seen · 80 lines · 127 tokens per session scan A 70d18adcf0d7

Subscribe to this mod's changes

confidence-check is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 693 once invoked, about $0.0006 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens