gap-scanner

gap-scanner is a skill for Claude Code, Codex from MrBinnacle/azimuth. It costs 55 tokens per session (1,553 once invoked), scanned A, original, MIT.

A coverage-audit guide for AZIMUTH, a project that uses reference, diagnostic, and policy files to support its decisions. It compares the areas claimed in SKILL.md with the material those files actually contain.

In plain words
What is it for?
Run it before planning a major version to produce a structured gap report. It identifies mismatches but does not suggest fixes.
Why use it?
A project can claim to cover more areas than its supporting material explains. This audit shows where coverage is thin, missing, or structurally inconsistent.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/mrbinnacle/azimuth/gap-scanner
Any agent
npx skills add MrBinnacle/azimuth --skill gap-scanner
Clone the repo
git clone --depth 1 https://github.com/MrBinnacle/azimuth

Made for: Claude Code, Codex.

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 gap-scanner

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrbinnacle/azimuth/gap-scanner.svg)](https://agentmods.dev/skills/mrbinnacle/azimuth/gap-scanner)
Your own site
<a href="https://agentmods.dev/skills/mrbinnacle/azimuth/gap-scanner"><img src="https://agentmods.dev/badge/skills/mrbinnacle/azimuth/gap-scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00055 $0.01553
Opus 5 $0.00028 $0.00776
Sonnet 5 $0.00011 $0.00311
Haiku 4.5 $0.00006 $0.00155

Measured 4d ago against content hash ad94d80e6117, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gap-scanner 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 4d 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/maintenance/gap-scanner/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gap Scanner

Find where AZIMUTH's stated coverage exceeds its actual reference support, and where reference material covers domains not yet claimed.

This skill reads files and produces a structured gap report. It does not propose fixes — it maps the delta between claims and reality.


Protocol

Run all 6 steps sequentially. Read each file group before drawing conclusions.


Step 1 — Extract Coverage Claims from SKILL.md

Read SKILL.md. Extract and list:

  1. Every decision type in "Use When"
  2. Every domain named in the DEEP mode load rules (tech/engineering → software-failure-patterns.md, product/launch → launch-risks.md, startup/venture → startup-failures.md)
  3. Every diagnostic load condition (which module trigger → which diagnostic file)
  4. Every domain-policy route (which Layer-3 domain → which file in domain-policies/)
  5. Every domain explicitly named in the base rate load rule

Step 2 — Audit Reference Files Against Claims

For each domain claimed in Step 1, read the corresponding reference file. Assess coverage depth:

  • STRONG: File provides specific patterns, mechanisms, and diagnostic questions for this domain
  • PARTIAL: File mentions the domain but coverage is thin, hedged, or missing mechanisms
  • THIN: Domain is in base-rates.md but has no corresponding pattern file
  • MISSING: Domain is claimed in SKILL.md but no reference material exists for it

Known gaps to confirm (from prior analysis):

  • M&A / Partnerships: base-rates.md has a full M&A section. Is M&A listed in SKILL.md "Use When"? Is there a pattern file for M&A failure modes? Is there a domain-policy?
  • IT / Infrastructure Migration: base-rates.md has a migration section. Is there a pattern file? A domain-policy?
  • Organizational Change: base-rates.md has an org change section. Is org restructure in SKILL.md "Use When"? Pattern file? Domain-policy?

For each gap found, record:

  • What is claimed (exact quote from SKILL.md)
  • What exists (file and coverage depth)
  • The delta

Read the full file on GitHub · 161 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. 4d ago First seen · 161 lines · 55 tokens per session scan A ad94d80e6117

Subscribe to this mod's changes

gap-scanner is a skill published in the GitHub repository MrBinnacle/azimuth (8 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,553 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

premortem

Run a premortem on any plan, launch, product, hire, strategy, or decision. Imagines it failed 6 months from now, works backward to find every reason why, then produces a revised plan. Triggers include "premortem this", "premortem my", "what could kill this", "stress test this plan", "find the blind spots", "poke holes…

b1rdmania/claude-premortem-skill · 117 tokens

pant-executive-decision-review

Pressure-test a product recommendation for an executive decision and rehearse the review. Use for approval, sponsorship, investment, priority, capacity, or commitment requests; not general roadmap or backlog review.

deanpeters/product-manager-antagonist-skills · 46 tokens

pant-antagonist-router

Select the smallest useful PANT skill, mode, entry path, pressure, and optional companion from a messy product-management request. Use when the correct pressure test or rehearsal is unclear.

deanpeters/product-manager-antagonist-skills · 42 tokens

pant-artifact-pressure-test

Pressure-test a product artifact, argument, or proposal when no specialist PANT scenario fits. Use for general grounding, contradictions, evidence, and readiness; not work clearly served by a specialist.

deanpeters/product-manager-antagonist-skills · 44 tokens

pant-business-case-review

Pressure-test a product investment business case and rehearse its review. Use for benefits, costs, alternatives, economics, uncertainty, adoption, ownership, and decision conditions; not a whole business model.

deanpeters/product-manager-antagonist-skills · 44 tokens

pant-market-sizing-review

Pressure-test TAM, SAM, SOM, and other market estimates. Use for market definition, segmentation, provenance, reachability, pricing, conversion, timing, sensitivity, and decision relevance; not generic market research.

deanpeters/product-manager-antagonist-skills · 47 tokens