consistency-check

consistency-check is a skill for Claude Code from pitimon/8-habit-ai-dev. It costs 142 tokens per session (3,241 once invoked), scanned A, original, MIT.

A consistency checker for related project documents, such as a product requirements document, design, and task list. It can also compare symptoms, evidence, root cause, fixes, and verification for operational hotfixes.

In plain words
What is it for?
Checking persisted requirements, design, and breakdown artifacts for the same feature, or reviewing an incident/configuration hotfix for matching evidence and verification.
Why use it?
It finds contradictions or missing links between documents and incident claims before implementation or merge. This prevents teams from building from requirements that quietly disagree.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the 8-habit-ai-dev plugin — 24 skills, 2 agents, 1 hook shipped together

Good fit Checking persisted requirements, design, and breakdown artifacts for the same feature, or reviewing an incident/configuration hotfix for matching evidence and verification.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pitimon/8-habit-ai-dev
Claude Code
/plugin install 8-habit-ai-dev

Made for: Claude Code.

Or install 8-habit-ai-dev, the plugin that ships this one along with the rest of its 24 skills, 2 agents, 1 hook.

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-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/consistency-check/github.svg)](https://agentmods.dev/skills/pitimon/8-habit-ai-dev/consistency-check)
Your own site
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/consistency-check"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/consistency-check/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 consistency-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/consistency-check"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/consistency-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,241 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 $0.00142 $0.03241
Opus 5 $0.00071 $0.01621
Sonnet 5 $0.00028 $0.00648
Haiku 4.5 $0.00014 $0.00324

Measured 8d ago against content hash e7dc26ed7732, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

consistency-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 8d 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.

plugin/skills/consistency-check/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Artifact Consistency Check

Habits: H5 (Seek First to Understand) + H1 (Be Proactive) | Anti-pattern: Implementing from a PRD/design/tasks bundle that quietly contradicts itself.

When to Use

  • After /requirements, /design, and /breakdown have all been run with --persist <slug> for the same feature
  • Before starting implementation on a multi-artifact feature, especially across sessions
  • When auditing whether a design actually covers all stated requirements
  • When onboarding a new team member to an in-flight spec
  • During PR review when the PR description references a docs/specs/<slug>/ directory
  • Before merging or closing an incident/config hotfix PR that needs symptom ↔ evidence ↔ root cause ↔ fix ↔ verification alignment
  • When alerting, notification, deploy, or runtime-config text risks over-claiming what live verification proves

When to Skip

  • Single-artifact work (no cross-artifact relationship to check)
  • Bug fixes with no spec persisted and no incident/config/deploy/verification claims to reconcile
  • Specs that did not opt into --persist (this skill requires persisted files — emits a CRITICAL with guidance if directory empty)

Mode Selection

Use spec-artifact mode when the input is a docs/specs/<slug>/ directory or path containing prd.md, design.md, or tasks.md.

Use incident/config hotfix mode when the input is an issue, PR, changelog entry, deploy note, alert, or operator summary instead of a persisted spec bundle. This mode is read-only and works without docs/specs/<slug>/.

Input Resolution

/8-habit-ai-dev:consistency-check <arg> — auto-detect:

  1. If <arg> matches an existing directory entry under docs/specs/<arg>/, treat as slug and read from docs/specs/<arg>/
  2. Otherwise, treat <arg> as a directory path (relative or absolute) and read from that path
  3. If neither resolves to an existing directory containing at least one of prd.md, design.md, tasks.md, switch to incident/config hotfix mode if the user supplied incident, PR, deploy, alert, or verification material; otherwise emit a single CRITICAL finding "No persisted artifacts found at <resolved-path> — was '--persist <slug>' used during /requirements/design/breakdown, or did you intend incident/config hotfix mode? See guides/persistence-convention.md" and exit cleanly

Read the full file on GitHub · 207 lines

Files

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.

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. 8d ago First seen · 207 lines · 142 tokens per session scan A e7dc26ed7732

Subscribe to this mod's changes

consistency-check is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 3,241 once invoked, about $0.0007 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.