consistency-check

consistency-check is a skill for Claude Code from pssah4/digital-innovation-agents. It costs 82 tokens per session (7,809 once invoked), scanned A, original, MIT.

A checker for links between project records such as requirements, architecture decisions, plans, backlog items, and source-code files. It can look for missing, unused, or outdated connections.

In plain words
What is it for?
Use it for consistency checks, finding dead links and orphaned features, checking the project before release, or running an on-demand graph review.
Why use it?
It helps reveal when project documentation and code have drifted apart, or when an item has no supporting record.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Part of the digital-innovation-agents plugin — 13 skills, 1 hook shipped together

Good fit Use it for consistency checks, finding dead links and orphaned features, checking the project before release, or running an on-demand graph review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pssah4/digital-innovation-agents/consistency-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.

Any agent
npx skills add pssah4/digital-innovation-agents --skill consistency-check
Clone the repo
git clone --depth 1 https://github.com/pssah4/digital-innovation-agents

Made for: Claude Code.

Or install digital-innovation-agents, the plugin that ships this one along with the rest of its 13 skills, 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/pssah4/digital-innovation-agents/consistency-check/github.svg)](https://agentmods.dev/skills/pssah4/digital-innovation-agents/consistency-check)
Your own site
<a href="https://agentmods.dev/skills/pssah4/digital-innovation-agents/consistency-check"><img src="https://agentmods.dev/badge/skills/pssah4/digital-innovation-agents/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/pssah4/digital-innovation-agents/consistency-check"><img src="https://agentmods.dev/badge/skills/pssah4/digital-innovation-agents/consistency-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,809 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 29
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 508
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Excessive Agency · line 89
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 195
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 188
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 193
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00082 $0.07809
Opus 5 $0.00041 $0.03904
Sonnet 5 $0.00016 $0.01562
Haiku 4.5 $0.00008 $0.00781

Measured 12d ago against content hash 57846bea9d5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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.

skills/consistency-check/SKILL.md · 632 lines

How it starts

The opening of the file, as written. The whole thing — 632 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consistency Check

This skill treats the V-Model artifacts as a graph. Nodes are artifacts (BA sections, Epics, Features, Success Criteria, ADRs, arc42 sections, PLANs, Backlog items, Code files). Edges are references (Epic→Feature, Feature→ADR, Feature→Code via source paths, BL-Item→Feature, and so on). The check answers one question: is the graph complete and consistent, or do we have orphans, dead links, and semantic drift?

The skill is an explicit user command. It runs mandatorily once per cycle before release (security-audit Step 7 / Closing Handoff) and on demand any time. Between those points, the pre-commit hook enforces the drift-critical invariants (script-only, no skill load); phase skills do NOT invoke this skill at their boundaries.

Writing style: Every artifact this skill writes follows the rules in skills/project-conventions/SKILL.md under "Writing style". No em dashes, no AI vocabulary, ASCII for umlauts if the existing project convention uses ASCII.

Three modes

  • Mode A (syntactic, default): fast, no LLM, runs via the pre-commit hook, before release, and on demand.
  • Mode B (semantic, on-demand): agent-based, runs before release or on explicit --deep.
  • Mode C (interactive fix-loop): guided fix workflow with per-finding AskUserQuestion, Pro/Con suggestions, skip and custom-message options. Triggered by --fix-interactive or after a pre-commit hook block.

Mode reference

Mode A: Syntactic check (default, fast, no LLM)

Runs via the pre-commit hook, before release, and on demand. Uses Grep + filesystem probes only. Costs near zero.

Checks (8 quick-check items):

  1. Dead links. Every Markdown link to a project-internal path (_devprocess/..., src/..., docs/...) points to an existing file.
  2. Backlog completeness. Every artifact file under _devprocess/requirements/, _devprocess/architecture/, _devprocess/implementation/plans/, _devprocess/requirements/fixes/, and _devprocess/requirements/improvements/ has exactly one row in the backlog. No artifact without a row, no row without an artifact.
  3. Backlog as single source. Artifact frontmatter does NOT carry status: or phase: fields. The backlog row is authoritative. Frontmatter that duplicates these fields gets flagged.
  4. Spec references valid. Every Feature references a real Epic ID. Every Backlog Refs entry resolves to an existing row or file. Every PLAN's feature-refs, adr-refs, fix-refs, and imp-refs resolve.
  5. ADR references valid. Every ADR ID listed in a FEATURE's adr-refs, in arc42 Par. 9 table, in JSDoc headers, or in src/ARCHITECTURE.map resolves to an existing ADR file.
  6. ADR contradictions. No two ADRs cover overlapping topics with opposing decisions. Heuristic: similar titles or matching triggering-asr clusters surfaced for human review.
  7. ADR abstraction rule. No ADR contains code paths (src/... strings, file basenames, line numbers, method signatures) in the core sections (Context, Decision Drivers, Considered Options, Decision, Consequences). Code paths in the ## Implementation Notes appendix are exempt.
  8. Backlog graph health. Every Refs entry in the backlog points at an existing row. The graph derived from the Refs columns is acyclic (Epic -> Feature -> Plan -> Fix forms a DAG).

Read the full file on GitHub · 632 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. 12d ago First seen · 632 lines · 82 tokens per session scan A 57846bea9d5d

Subscribe to this mod's changes

consistency-check is a skill published in the GitHub repository pssah4/digital-innovation-agents (39 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 7,809 once invoked, about $0.0004 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 2026-08-30.