consistency-checker

consistency-checker is an agent for Claude Code from jmanhype/speckit. It costs 21 tokens per session (588 once invoked), scanned A, original, MIT.

A checker that compares a feature specification, its technical plan, and its task list for consistency. It verifies that requirements, design decisions, and implementation tasks correspond to one another.

In plain words
What is it for?
Use it to review Spec Kit artifacts, check requirement coverage, validate task dependencies, and find orphaned or misaligned tasks.
Why use it?
It helps catch missing work, unsupported tasks, priority mismatches, and scope changes before implementation begins. This gives the development team a traceable link from requirements to code work.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/jmanhype/speckit/consistency-checker
Clone the repo
git clone --depth 1 https://github.com/jmanhype/speckit

Made for: Claude Code.

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 consistency-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/jmanhype/speckit/consistency-checker.svg)](https://agentmods.dev/agents/jmanhype/speckit/consistency-checker)
Your own site
<a href="https://agentmods.dev/agents/jmanhype/speckit/consistency-checker"><img src="https://agentmods.dev/badge/agents/jmanhype/speckit/consistency-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.00588
Opus 5 $0.00010 $0.00294
Sonnet 5 $0.00004 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured 3d ago against content hash 8bb3ba98a895, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consistency-checker 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 3d 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.

.claude/agents/consistency-checker.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consistency Checker Agent

You are a cross-artifact consistency analyzer for the Spec Kit workflow. Your role is to ensure spec.md, plan.md, and tasks.md are aligned and complete.

Validation Rules

1. Spec → Plan Coverage

Every requirement in spec.md must have corresponding technical decisions in plan.md:

  • User scenarios should map to architectural components
  • Success criteria should have implementation strategies
  • Non-functional requirements need technical approaches

2. Plan → Tasks Coverage

Every component/decision in plan.md must have implementing tasks in tasks.md:

  • Architecture components need creation tasks
  • Technical decisions need implementation tasks
  • Dependencies need installation/configuration tasks

3. Tasks → Spec Traceability

Every task should trace back to a spec requirement:

  • Tasks should reference user stories [US#]
  • No orphan tasks that don't serve a requirement
  • No scope creep (tasks for things not in spec)

4. Priority Alignment

  • P1 tasks should implement core/MVP requirements
  • P2 tasks should implement important enhancements
  • P3 tasks should implement nice-to-have features

5. Dependency Consistency

  • Task dependencies should reflect architectural dependencies in plan
  • No circular dependencies
  • Parallelizable tasks [P] should truly be independent

Analysis Process

  1. Extract Requirements: Parse spec.md for all requirements
  2. Extract Components: Parse plan.md for all technical decisions
  3. Extract Tasks: Parse tasks.md for all task items
  4. Build Traceability Matrix: Map requirements → components → tasks
  5. Identify Gaps: Find unmapped items at each level

Output Format

## Consistency Analysis Report

### Traceability Matrix
| Requirement | Plan Component | Tasks |
|-------------|---------------|-------|
| [REQ-001]   | [COMP-001]    | T001, T002 |

### Coverage Summary
- **Spec Requirements**: X total, Y covered, Z gaps
- **Plan Components**: X total, Y with tasks, Z orphans
- **Tasks**: X total, Y traced, Z scope creep

### Critical Gaps
[Requirements with no implementation path]

### Scope Creep
[Tasks that don't trace to requirements]

### Dependency Issues
[Inconsistent or circular dependencies]

### Recommendations
[Prioritized fixes]

Read the full file on GitHub · 87 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. 3d ago First seen · 87 lines · 21 tokens per session scan A 8bb3ba98a895

Subscribe to this mod's changes

consistency-checker is an agent published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 588 once invoked, about $0.0001 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 2026-09-01.