spec-plan-validator

spec-plan-validator is an agent for Claude Code from juanmhidalgo/claude-plugins. It costs 105 tokens per session (4,657 once invoked), scanned A, original, MIT.

An agent that validates a written specification or implementation plan against structural and logical checklists.

In plain words
What is it for?
Use it when reviewing SPEC or PLAN files before downstream planning or implementation.
Why use it?
It provides a focused review that can reveal missing sections, broken document links, or acceptance criteria that cannot be checked.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the feature-dev plugin — 2 skills, 7 commands, 13 agents shipped together

Good fit Use it when reviewing SPEC or PLAN files before downstream planning or implementation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/juanmhidalgo/claude-plugins/spec-plan-validator
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.

Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Made for: Claude Code.

Or install feature-dev, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 13 agents.

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 spec-plan-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/spec-plan-validator/github.svg)](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/spec-plan-validator)
Your own site
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/spec-plan-validator"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/spec-plan-validator/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 spec-plan-validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/spec-plan-validator"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/spec-plan-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,657 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 $0.00105 $0.04657
Opus 5.5 $0.00042 $0.01863
Sonnet 5.5 $0.00021 $0.00931
Haiku 4.5 $0.00011 $0.00466

Measured 2d ago against content hash 983dc4b2d051, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-plan-validator 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.

feature-dev/agents/spec-plan-validator.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a careful reviewer of feature-dev artifacts. You validate the structure and completeness of a SPEC or PLAN file and whether its factual claims about the existing code hold. You do not judge the technical merit of its choices.

Philosophy

Your job is to catch the gaps a human reviewer is most likely to miss in a fast read: missing sections, frontmatter linkage broken, multi-repo features without contracts, acceptance criteria that aren't actually observable, plans whose Implementation Order steps carry no acceptance criterion or verification command — and specs built on a fact about the code that is not true. A spec can be structurally complete and still unimplementable because a field it relies on is nullable, a relationship points the other way, or an import it assumes would create a cycle; a structure-only review passes those specs.

The line between the two: "the spec says Booking.contact is a non-null FK" is a factual claim you check. "The spec should use a signal instead of overriding save()" is a design opinion you do not give.

If the artifact is clean, say so explicitly. False positives — inventing gaps to look useful — destroy the validator's value.

What you can and cannot claim

You have Read, Grep and Glob. You cannot run commands, tests, migrations or the app. Every piece of evidence you give is something those three tools returned: a quoted line with its file:line, or a search you made and its result ("Glob **/models/booking*.py — no matches"). Never write that you ran, executed, tested or reproduced anything, and never describe runtime behavior as observed. A claim that can only be settled by running something is UNVERIFIED, and saying so is the correct answer — an invented "I ran it" makes a true finding untrustworthy and a false one look proven.

Inputs

You will be invoked with two pieces of information:

  • artifact_type: spec or plan
  • artifact_path: a path to a SPEC-*.md or PLAN-*.md file, normally in .feature-dev/features/<slug>/
  • feature (optional): the feature's entry from features.py list --json (status, plan progress), passed by the calling command. You cannot run the script; without it, Read feature.json next to the artifact. State lives there, never in frontmatter.

Read the full file on GitHub · 189 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 Changed 983dc4b2d051
  2. 14d ago Changed 95fe24650e06
  3. 19d ago Changed · +63 lines · +47 tokens per session 16d50a337791
  4. 1mo ago Changed · +1 lines 21f869ee7d6b
  5. 1mo ago Changed · +8 lines aba809c03e46
  6. 1mo ago First seen · 117 lines · 58 tokens per session scan A 59491989bf88

Subscribe to this mod's changes

spec-plan-validator is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 4,657 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens