module-bound-check

module-bound-check is a skill for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 46 tokens per session (433 once invoked), scanned A, original, MIT.

A project checker for reviewing how requirements, designs, tests, and code are divided into modules. A module is a defined part of a software system.

In plain words
What is it for?
Use it before a substantial change in a regulated project to check five module-structure rules and report errors and warnings.
Why use it?
It finds decomposition problems, such as missing module assignments, invalid cross-module references, or code and specifications being grouped at mismatched levels.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sdlc-assured plugin — 8 skills shipped together

Good fit Use it before a substantial change in a regulated project to check five module-structure rules and report errors and warnings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stevegjones/ai-first-sdlc-practices/module-bound-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 SteveGJones/ai-first-sdlc-practices --skill module-bound-check
Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-assured, the plugin that ships this one along with the rest of its 8 skills.

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 module-bound-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/module-bound-check/github.svg)](https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/module-bound-check)
Your own site
<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/module-bound-check"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/module-bound-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 module-bound-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/module-bound-check"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/module-bound-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 433 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 pass 7 Sept 2026
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 $0.00046 $0.00433
Opus 5 $0.00023 $0.00217
Sonnet 5 $0.00009 $0.00087
Haiku 4.5 $0.00005 $0.00043

Measured 9d ago against content hash 17f2cab28e0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

module-bound-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 9d 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.

plugins/sdlc-assured/skills/module-bound-check/SKILL.md · 44 lines

What it actually says

Skill: module-bound-check

Use this skill to verify the project's decomposition is sound. Aggregates results from all 5 module-bound validators and reports a single pass/fail with per-validator detail. Run this before pushing a substantial change to a regulated-context project.

Steps

  1. Load the decomposition. Read programs.yaml (or use default_decomposition if absent).

  2. Build the spec_module_lookup. Walk all docs/specs/**/*.md artefacts; map each declared ID → module (from frontmatter or positional ID prefix).

  3. Build the import-edge graph. Walk source files; for each import, determine the from-module and to-module by mapping the file path to declared module paths.

  4. Run each validator.

    • req_has_module_assignment
    • code_annotation_maps_to_module
    • visibility_rule_enforcement (mode from team-config: strict for regulated, advisory otherwise)
    • anaemic_context_detection
    • granularity_match
  5. Aggregate results. Print a table:

    Validator                          Status   Errors  Warnings
    req_has_module_assignment          PASS     0       0
    code_annotation_maps_to_module     FAIL     2       0
    visibility_rule_enforcement        PASS     0       1
    anaemic_context_detection          PASS     0       0
    granularity_match                  PASS     0       3
    
  6. Report each error and warning with file path and line number.

Done criteria

  • All 5 validators ran.
  • Result table printed.
  • Exit code: 0 if all pass; 1 if any error; 0 if only warnings (warnings don't block).
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. 9d ago First seen · 44 lines · 46 tokens per session scan A 17f2cab28e0c

Subscribe to this mod's changes

module-bound-check is a skill published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 433 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 2026-08-30.