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 elct9620/ai-spec-skills --skill spec-qualitygit clone --depth 1 https://github.com/elct9620/ai-spec-skillsWrote 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/elct9620/ai-spec-skills/spec-quality)<a href="https://agentmods.dev/skills/elct9620/ai-spec-skills/spec-quality"><img src="https://agentmods.dev/badge/skills/elct9620/ai-spec-skills/spec-quality/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/elct9620/ai-spec-skills/spec-quality"><img src="https://agentmods.dev/badge/skills/elct9620/ai-spec-skills/spec-quality.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 | $0.00031 | $0.02334 |
| Opus 5 | $0.00015 | $0.01167 |
| Sonnet 5 | $0.00006 | $0.00467 |
| Haiku 4.5 | $0.00003 | $0.00233 |
Grade A, and why
spec-quality 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 11d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specification Quality
Criteria and tools for evaluating specification quality.
Applicability Rubric
| Condition | Pass | Fail |
|---|---|---|
| Spec review requested | Need to assess spec quality | No review needed |
| Pre-implementation check | Spec about to be implemented | Already implemented |
| Quality gate | Spec must meet minimum bar before proceeding | Quality already verified |
| Improvement cycle | Iterating on spec after feedback | No prior version to compare against |
Apply when: Any condition passes
Core Principles
Specification Rubric
Rate each item Y (yes) or N (no).
Intent Layer
| # | Criterion | Required | Y/N |
|---|---|---|---|
| 1 | Purpose stated in one sentence? | ✓ | |
| 2 | Target users identified? | ✓ | |
| 3 | Impacts (behavior changes) identified? | ||
| 4 | Success criteria measurable or verifiable? |
Design Layer
| # | Criterion | Required | Y/N |
|---|---|---|---|
| 5 | Each documented feature has defined behavior? | ✓ | |
| 6 | Error scenarios cover all documented features? | ✓ | |
| 7 | Interaction points (internal and external) have explicit contracts? | ||
| 8 | Implementer can build without clarifying questions? | ✓ |
Consistency Layer
| # | Criterion | Required | Y/N |
|---|---|---|---|
| 9 | Key terms defined and used consistently throughout? | ||
| 10 | Recurring situations have named patterns? | ||
| 11 | Two implementers would produce compatible results? |
Evidence Criteria for Y/N scoring:
Score based on the spec's declared scope — what the spec claims to cover. Do not score N because the spec omits something outside its declared scope.
| # | Score Y when | Score N when |
|---|---|---|
| 1 | Spec contains an explicit sentence stating what problem the system solves | No purpose statement, or purpose restates the feature name ("A login system for logging in") |
| 2 | Spec names specific user roles or personas | "Users" mentioned generically without identifying who or what they accomplish |
| 3 | Spec lists observable behavior changes or measurable outcomes | No impacts listed, or only vague goals ("improve performance") |
| 4 | Success criteria use numbers, conditions, or verifiable statements | Unmeasurable criteria ("fast and reliable", "good UX") |
| 5 | Every feature the spec lists has at least one defined behavior (action → result) | Features listed as bullet points without behavior definitions |
| 6 | Each documented feature has at least one error/failure scenario defined | Missing error handling for documented features, or only generic "handle errors appropriately" |
| 7 | Module interaction points described in the spec have explicit input/output contracts | Modules interact without defined interfaces |
| 8 | An implementer could build the documented scope without asking clarifying questions | Ambiguous terms, undefined states, or missing decisions within documented scope |
| 9 | Key domain terms are defined; each concept has exactly one name throughout | Same concept called different names in different sections |
| 10 | Similar situations within the spec reference shared patterns or conventions | Ad-hoc solutions for similar problems in different sections |
| 11 | Two implementers would produce compatible results for all documented behaviors | Interpretation would vary for documented scope |
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.
- 11d ago First seen · 166 lines · 31 tokens per session scan A 04fc8634ae2a
spec-quality is a skill published in the GitHub repository elct9620/ai-spec-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,334 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…