incoherence-detector

incoherence-detector is a skill for Claude Code from rtazima/claude-proj-blueprint. It costs 0 tokens per session (872 once invoked), scanned A, original, MIT.

A consistency checker for comparing planned requirements, project documentation, and the code that actually runs.

In plain words
What is it for?
Use it to review PRDs, architecture decision records, API specifications, READMEs, configuration examples, source files, tests, and runbooks for mismatches.
Why use it?
It helps find drift, such as a feature promised in a specification but missing from code, or code and documentation that no longer agree.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

Good fit Use it to review PRDs, architecture decision records, API specifications, READMEs, configuration examples, source files, tests, and runbooks for mismatches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rtazima/claude-proj-blueprint/incoherence-detector
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.

Any agent
npx skills add rtazima/claude-proj-blueprint --skill incoherence-detector
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

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 incoherence-detector

README.md
[![agentmods](https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/incoherence-detector/github.svg)](https://agentmods.dev/skills/rtazima/claude-proj-blueprint/incoherence-detector)
Your own site
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/incoherence-detector"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/incoherence-detector/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 incoherence-detector

Your own site · 80×15
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/incoherence-detector"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/incoherence-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 872 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 $0.00872
Opus 5 $0.00000 $0.00436
Sonnet 5 $0.00000 $0.00174
Haiku 4.5 $0.00000 $0.00087

Measured 10d ago against content hash d20ce1db348e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

incoherence-detector 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 10d 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/skills/incoherence-detector/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incoherence Detector

Activated when: "check consistency", "find mismatches", "incoherence", "specs match code", "docs outdated", "sync check", "drift".

Purpose

Detect mismatches between three layers:

  1. Specs — What we said we'd build (PRDs, API specs, schemas)
  2. Docs — What we say it does (CLAUDE.md, README, ADRs, runbooks)
  3. Code — What it actually does (source files, tests, config)

Workflow

Phase 1: Inventory (gather sources)

For the target module/feature, collect:

  • PRD in docs/product/
  • Relevant ADRs in docs/architecture/
  • API spec in docs/specs/api/ (if applicable)
  • CLAUDE.md sections mentioning the module
  • README.md sections mentioning the module
  • Source files implementing the feature
  • Test files covering the feature
  • .env.example entries (if applicable)
  • Runbooks referencing the feature

Phase 2: Cross-reference (find mismatches)

Check each pair:

Spec <> Code:

  • Features listed in PRD but not implemented
  • Features implemented but not in any PRD
  • API endpoints in spec but missing from code
  • API endpoints in code but missing from spec
  • Data models in spec vs actual schema/types
  • Acceptance criteria in PRD vs test coverage

Docs <> Code:

  • Commands documented but not working
  • Commands working but not documented
  • Env vars in code but missing from .env.example
  • Env vars in .env.example but unused in code
  • Module map in CLAUDE.md vs actual file structure
  • Gotchas in CLAUDE.md vs actual behavior
  • Architecture in ADRs vs current implementation

Spec <> Docs:

  • PRD requirements not reflected in docs
  • Docs describing features not in any PRD
  • Version/status mismatches (PRD says "planned", docs say "done")
  • Naming inconsistencies between PRD and docs

Phase 3: Classify findings

For each mismatch found:

  • DRIFT — Code evolved past the spec. Spec needs updating.
  • MISSING — Spec/doc promises something not yet implemented.
  • STALE — Documentation describes old behavior.
  • CONFLICT — Two sources contradict each other.
  • ORPHAN — Implementation exists with no spec or doc.

Read the full file on GitHub · 94 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. 10d ago First seen · 94 lines · 0 tokens per session scan A d20ce1db348e

Subscribe to this mod's changes

incoherence-detector is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 872 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 2026-08-30.

Related

Other skills, from other repositories

printing-press-output-review

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…

mvanhorn/cli-printing-press · 102 tokens

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

issue-root-resolution

Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.

Gentleman-Programming/gentle-ai · 45 tokens

rdd-defect-workflow

Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.

Gentleman-Programming/gentle-ai · 41 tokens

review-loop

Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…

sangrokjung/claude-forge · 100 tokens

truecourse-analyze

Run TrueCourse architecture analysis on this repository.

truecourse-ai/truecourse · 13 tokens