agentmods.dev

cross-verify

cross-verify is a skill for Claude Code from pitimon/8-habit-ai-dev. It costs 39 tokens per session (3,016 once invoked), scanned A, original, MIT.

A 17-question review checklist for checking a plan or implementation from the plugin’s eight working principles.

In plain words
What is it for?
Use it after planning, before starting a multi-file change, or before opening a pull request; skip it for obvious one-line fixes and routine formatting changes.
Why use it?
It gives you a structured quality check before implementation or a pull request, helping reveal gaps that are easy to miss from one viewpoint.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Codex.

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

not rated 3repo 1mo ago A scan 39 tokens original MIT

Good fit Use it after planning, before starting a multi-file change, or before opening a pull request; skip it for obvious one-line fixes and routine formatting changes.

Compare 6 skills from other repositories ↓
View source ↗ pitimon/8-habit-ai-dev
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 cross-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/cross-verify.svg)](https://agentmods.dev/skills/pitimon/8-habit-ai-dev/cross-verify)
Your own site
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/cross-verify"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/cross-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,016 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 $0.00039 $0.03016
Opus 5 $0.00019 $0.01508
Sonnet 5 $0.00008 $0.00603
Haiku 4.5 $0.00004 $0.00302

Measured 7d ago against content hash 51f5235207bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cross-verify 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 7d 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/cross-verify/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Verify (8-Habit Checklist)

All Habits | Anti-pattern: Shipping without reflecting on quality from multiple perspectives

When to Use

  • After writing a plan, before starting implementation
  • Before creating a PR for a multi-file change
  • When something feels off but you can't pinpoint why

When to Skip

  • Single-line bug fixes with obvious root cause
  • Formatting or linting changes
  • Dependency version bumps with passing CI

Auto-Detection (Structured Output Blocks)

Before running the manual checklist, search for structured output blocks in the current directory:

  1. Glob for the persisted artifact files: docs/specs/*/prd.md, docs/specs/*/design.md, docs/specs/*/tasks.md (plus their *.vN.md conflict variants — the canonical --persist targets), and *-review.md / *-prd.md / *-tasks.md in the working directory for hand-saved reports
  2. Read each file and look for <!-- SKILL_OUTPUT: blocks. As of v2.21.39 (#375) these blocks live in the persisted files only, not the conversation transcript — a non-persisted run has no block, which is expected and falls through to the session-context fallback and, failing that, manual assessment (steps 5–6)
  3. If found, pre-populate evidence for:
    • Q4: Extract ears_count and success_criteria_count from requirements block
    • Q5: Extract test_coverage_checked from review block
    • Q8: Compare task_count vs ears_count for scope alignment — flag if task_count > ears_count * 3
    • Q14: Extract decision_count from design block — flag if only 1 option was presented (no third alternative considered)
    • Q16: Extract sticky_decisions from design block — flag if 0 sticky decisions in a design with >3 decisions (WHY not captured)
    • Q4: Cross-check decision_count against requirements success_criteria_count — flag if decisions don't cover all criteria
  4. Mark auto-populated answers with ✓A (auto-detected) confidence level
  5. Session-context fallback (no persisted block): if no file block was found but the producer skills (/requirements, /design, /breakdown, /review-ai) ran earlier in this session, mine their conversation output — the PRD / design / tasks prose still in context — to pre-populate Q4 / Q8 / Q14 / Q16. Mark ✓I (inferred from prose), or ✓A only for fields the prose states as an explicit count (e.g. a numbered EARS list). This is runtime-neutral: it reads prose, not the HTML-comment block, so it works identically in Codex. (v2.21.42, #375 follow-up — restores the same-session auto-populate that file-only emission removed, without runtime-conditional producer behavior.)
  6. If neither a persisted block nor prior producer output is available, proceed with manual assessment (no change to prior behavior)

Read the full file on GitHub · 176 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. 7d ago First seen · 176 lines · 39 tokens per session scan A 51f5235207bb

Subscribe to this mod's changes

cross-verify is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 3,016 once invoked, about $0.0002 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.

Claude CodeTestingai-developmentanti-vibe-codingclaude-code-plugindeveloper-tools
Related

Other skills, from other repositories

crap-analyzer

Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …

swingerman/engineer · 109 tokens

loop-test

A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.

restarter/lets-workflow · 112 tokens

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code.

DollarDill/beads-superpowers · 21 tokens

joycraft-implement-level5

Invoked by tune's roadmap or the human opting into Level 5 — set up the autofix loop, holdout scenario testing, and scenario evolution from specs.

maksutovic/joycraft · 39 tokens

coverage-check

Run the repo's unit tests with coverage and verify that every file touched in the current change keeps line, branch, and function coverage at or above 95%. Language- and framework-agnostic. Use before committing, before PR creation, or when the user asks about coverage.

theam/claude-dev-kit · 59 tokens

harness-validate

Use when user invokes /harness-validate or wants to check whether a harness.yaml file is valid according to the Harness Protocol v1 JSON Schema. Reports validation errors with field paths and helpful fix suggestions.

harnessprotocol/harness-kit · 46 tokens