A command that looks for contradictions between documents from different project phases. It compares items such as planned features, architecture, implementation details, threats, and security protections.

Use it as an optional review before a project gate. It needs at least two completed phases and their phase-index documents.

It catches disagreements that checks within one document or phase may miss. This helps reveal gaps between what the project says it will do and how it is designed or built.

cross-check — Command for Claude Code by jonase47/ccpr

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/jonase47/ccpr

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jonase47/ccpr/cross-check/github.svg)](https://agentmods.dev/commands/jonase47/ccpr/cross-check)

Your own site

<a href="https://agentmods.dev/commands/jonase47/ccpr/cross-check"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/cross-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/jonase47/ccpr/cross-check"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/cross-check.svg" alt="Reviewed on agentmods" width="80" 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 2,268 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.02268
Opus 5.5	$0.00000	$0.00907
Sonnet 5.5	$0.00000	$0.00454
Haiku 4.5	$0.00000	$0.00227

Measured 1mo ago against content hash 977753dd5b52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cross-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 1mo 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.

commands/cross-check.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cross-check – Cross-Artifact Consistency Check Across Phases

Reads phase indexes and selected detail files, checks inconsistencies between phases (architecture ↔ implementation, features ↔ stories, threats ↔ mitigations, etc.).

Bridges the gap between intra-phase lints (phase-docs-lint.sh) and gate content evaluation — finds contradictions no other command surfaces.

Recommendation, not a mandatory step. Gates list /cross-check as an optional pre-flight check.

Argument: $ARGUMENTS = [optional: projectdir]

Without argument: operates on $(pwd).

Prerequisites

Project has at least 2 completed phases (otherwise there is no "cross")
Phase indexes exist: docs/discovery/DISCOVERY.md, docs/concept/CONCEPT.md, docs/architecture/ARCHITECTURE.md, docs/planning/PROJECT_PLAN.md, optionally docs/quality/QA.md
Optional: docs/CONSTITUTION.md (for R6)

Lead Agent

code-reviewer with system-architekt as consultant for tech-specific findings.

Rule Catalogue v1 (7 Rules)

R1: FEATURES.md ↔ AUTH.md / User-Stories

Every user-facing feature (login, profile, permissions) must have a corresponding flow in AUTH.md.

Sources:

docs/concept/FEATURES.md (feature list, MoSCoW)
docs/architecture/AUTH.md (auth flows)
docs/planning/BACKLOG.md (user stories as cross-reference)

Check: For each feature tagged as user-facing (heuristic: mentions "login", "account", "profile", "sign-in") → is a matching flow described in AUTH.md?

R2: TECH_STACK.md ↔ DATA_MODEL.md (DB choice consistent)

If TECH_STACK.md names PostgreSQL, DATA_MODEL.md must not use MongoDB syntax (and vice versa).

Sources:

docs/architecture/TECH_STACK.md (DB choice, language, framework)
docs/architecture/DATA_MODEL.md (schema, ERD)
docs/architecture/API_SPEC.md (endpoints)

Check: Extract DB term from TECH_STACK (regex PostgreSQL|MongoDB|SQLite|SwiftData|MySQL); search DATA_MODEL for syntax markers (CREATE TABLE, NoSQL JSON schema, @Model SwiftData decorators). Report inconsistencies.

Read the full file on GitHub · 199 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.

1mo ago Changed 977753dd5b52
1mo ago Changed f2e423d01a79
1mo ago First seen · 199 lines · 0 tokens per session scan A fde93002221d

Subscribe to this mod's changes

cross-check is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,268 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 2026-08-31.

Claude Code Planning agentic-workflows ai-agents anthropic claude claude-code-agents

stats

Show real token usage, delegation rate, and actual savings for the current Hydra session (parses Claude Code session JSONL — no AI estimation).

AR6420/Hail_Hydra · 29 tokens

map

View, rebuild, or query the codebase dependency map.

AR6420/Hail_Hydra · 11 tokens

design-intent

Guided UI/visual development with structured exploration, architecture design, and quality review.

joaquimscosta/arkhe-claude-plugins · 16 tokens

ralph

Ralph autonomous development loop with fresh context per iteration.

joaquimscosta/arkhe-claude-plugins · 10 tokens

debug

Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.

joaquimscosta/arkhe-claude-plugins · 48 tokens

double-check

Comprehensive verification with automated quality gates, confession gathering, and confidence-based issue filtering. Default: self-review with gates. --deep: multi-agent review via code-reviewer agent. Use before committing, after fixing bugs, or to validate feature completeness.

joaquimscosta/arkhe-claude-plugins · 50 tokens