spec-check

spec-check is a command for Claude Code from fatihkan/badi. It costs 0 tokens per session (431 once invoked), scanned A, original, MIT.

A check that compares the current code with a SPECIFICATION.md file, which describes the required features and acceptance conditions. It reports missing, incomplete, extra, or incorrectly implemented work.

In plain words
What is it for?
Use it to verify required features, non-goals, acceptance criteria, and related test coverage against the codebase.
Why use it?
It makes gaps and scope drift visible instead of relying on memory or a manual comparison.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the badi plugin — 81 skills, 86 commands, 30 agents, 7 hooks shipped together

Good fit Use it to verify required features, non-goals, acceptance criteria, and related test coverage against the codebase.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/fatihkan/badi/spec-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.

Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 81 skills, 86 commands, 30 agents, 7 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 spec-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/fatihkan/badi/spec-check.svg)](https://agentmods.dev/commands/fatihkan/badi/spec-check)
Your own site
<a href="https://agentmods.dev/commands/fatihkan/badi/spec-check"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/spec-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 431 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 $0.00000 $0.00431
Opus 5 $0.00000 $0.00216
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured today against content hash be97b9328680, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

spec-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 today.

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.

.claude/commands/spec-check.md · 72 lines

What it actually says

Specification conformance command. Audits the current code against SPECIFICATION.md, detecting feature gaps and scope drift.

Required Tools

  • Read (SPECIFICATION.md, source code)
  • Grep (feature search)
  • Glob (file scan)
  • Agent (auditor agent)
  • Bash (running tests)

Procedure (5 Steps)

Step 1: Load the Specification

  • Read docs/SPECIFICATION.md
  • Extract the core features (Must Have)
  • List the acceptance criteria
  • Identify the Non-Goals items

Step 2: Codebase Scan

For every "Must Have" feature:

  • Search for the related code (functions, routes, components)
  • Assess whether the acceptance criterion is met
  • Check test coverage

Step 3: Drift Detection

Missing Features:

  • Features in the spec but not found in the code

Scope Creep:

  • Features in the code but NOT in the spec
  • Things marked Non-Goals yet implemented anyway

Partial Implementations:

  • Features started but not finished
  • Implementations that fail the acceptance criteria

Step 4: Build the Conformance Report

A status per feature:

  • DONE — Acceptance criteria met
  • PARTIAL — Started but unfinished
  • MISSING — Not implemented yet
  • DRIFT — Implemented differently from the spec

Step 5: Action Suggestions

  • Prioritized missing-feature list
  • Scope-creep remediation suggestions
  • TaskBoard.md update (new tasks for the gaps)

Output Format

=== BADI SPEC CONFORMANCE CHECK ===
Specification: docs/SPECIFICATION.md
Date: [date]

Conformance Rate: [percent]%

Must Have: [done]/[total]
Should Have: [done]/[total]
Could Have: [done]/[total]

MISSING Features:
- [feature name] — [status]

DRIFT Findings:
- [drift description]

SCOPE CREEP:
- [marked non-goal but implemented]

Next: [priority action]
=========================================
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. today First seen · 72 lines · 0 tokens per session scan A be97b9328680

Subscribe to this mod's changes

spec-check is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 431 tokens. 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 2026-09-06.