Borrowing it
Nothing to install: this file belongs to adrian-d-hidalgo/nestjs-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adrian-d-hidalgo/nestjs-mcp-server/main/.claude/skills/spec-driven/SKILL.mdgit clone --depth 1 https://github.com/adrian-d-hidalgo/nestjs-mcp-serverWrote 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/adrian-d-hidalgo/nestjs-mcp-server/spec-driven)<a href="https://agentmods.dev/skills/adrian-d-hidalgo/nestjs-mcp-server/spec-driven"><img src="https://agentmods.dev/badge/skills/adrian-d-hidalgo/nestjs-mcp-server/spec-driven/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/adrian-d-hidalgo/nestjs-mcp-server/spec-driven"><img src="https://agentmods.dev/badge/skills/adrian-d-hidalgo/nestjs-mcp-server/spec-driven.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.05495 |
| Opus 5 | $0.00032 | $0.02747 |
| Sonnet 5 | $0.00013 | $0.01099 |
| Haiku 4.5 | $0.00006 | $0.00549 |
Grade A, and why
spec-driven 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 9d 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The GitHub issue is never modified. No SPEC, no summary, no pointer, no managed block. The issue is the requirement as its author wrote it; the SPEC is the analysis of how to satisfy it. Two artifacts with two owners and no synchronisation — which is precisely why they cannot drift out of agreement with each other.
The input is the accepted issue and its acceptance criteria; the OUTPUT is spec.md (plus
test-plan.md, whose shape the task-workspace skill owns). This is the analysis layer; it never
edits code. It sits between issue creation (/constitution) and implementation (/develop). GitHub
owns the issue's status and lifecycle; the task-workspace skill owns where the files live; this
skill owns what goes in the SPEC.
This project is a published npm library, which adds two axes no application-side SPEC needs:
what changes in the surface exported from src/index.ts, and what version bump that implies.
Those are Public API impact and SemVer impact, and they are the sections most likely to be
skipped and most expensive to get wrong.
| Input shape | Route |
|---|---|
| A consumer-visible defect | Open the issue FIRST (github-issues skill, Mode B via /debug); the SPEC then captures the supporting analysis in the workspace. |
| The symptom is a clear, certainty-bar-passable bug with an obvious one-line fix | Skip the SPEC — go straight to the issue, then /develop. |
| An accepted issue needs technical analysis before implementation | /specification <#N> — the specifier authors spec.md into the task workspace. |
| Root cause not obvious from a single Read pass | Bug-shaped SPEC — the debugger consult is the default (bug-diagnosis skill). |
| Anything touching the exported surface | Always a SPEC. Public API impact and SemVer impact are not decisions to make mid-implementation. |
The issue owns execution (state + labels) and the public contract; spec.md owns the technical
analysis. Two artifacts with two audiences — not one duplicated in two places.
Output: .project/tasks/issue-<N>/spec.md. See <WriteMechanic>.
Output: the same spec.md, updated in place. Nothing else changes — there is no second copy
anywhere to keep in step, which is the main practical benefit of the SPEC being a file rather than
issue content.
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.
- 9d ago First seen · 392 lines · 64 tokens per session scan A 7b3088086827
spec-driven is a skill published in the GitHub repository adrian-d-hidalgo/nestjs-mcp-server (38 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 5,495 once invoked, about $0.0003 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
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…