source-completeness

source-completeness is a skill for Claude Code from prime-radiant-inc/greenfield. It costs 60 tokens per session (1,955 once invoked), scanned A, original, Apache-2.0.

A check that compares a program’s source code with its behavioral specifications, which describe what users can interact with. It looks for missing commands, tools, settings, environment variables, command-line options, events, and error types.

In plain words
What is it for?
Use it to validate tool catalogs, configuration documentation, command-line interfaces, environment-variable lists, event inventories, and error documentation against the source code.
Why use it?
It catches user-facing features that the analysis and documentation process failed to record. It is intended to run after detailed specifications are written and before sanitization.

Skill for Claude Code

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

Part of the greenfield plugin — 22 skills, 2 commands, 2 agents shipped together

Good fit Use it to validate tool catalogs, configuration documentation, command-line interfaces, environment-variable lists, event inventories, and error documentation against the source code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/prime-radiant-inc/greenfield/source-completeness
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 prime-radiant-inc/greenfield --skill source-completeness
Clone the repo
git clone --depth 1 https://github.com/prime-radiant-inc/greenfield

Made for: Claude Code.

Or install greenfield, the plugin that ships this one along with the rest of its 22 skills, 2 commands, 2 agents.

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 source-completeness

README.md
[![agentmods](https://agentmods.dev/badge/skills/prime-radiant-inc/greenfield/source-completeness.svg)](https://agentmods.dev/skills/prime-radiant-inc/greenfield/source-completeness)
Your own site
<a href="https://agentmods.dev/skills/prime-radiant-inc/greenfield/source-completeness"><img src="https://agentmods.dev/badge/skills/prime-radiant-inc/greenfield/source-completeness.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,955 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 $0.00060 $0.01955
Opus 5 $0.00030 $0.00978
Sonnet 5 $0.00012 $0.00391
Haiku 4.5 $0.00006 $0.00196

Measured 8d ago against content hash b19104e39053, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

source-completeness 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 8d 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/source-completeness/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source-to-Spec Completeness Validation

Why This Exists

The analysis pipeline (Layers 1-3) reads source code and produces behavioral specs. But it can miss things:

  • Registered commands or tools defined in source but not in the tool catalog
  • Environment variables read by the code but not documented
  • CLI flags defined in the argument parser but not cataloged
  • Subcommands registered dynamically or conditionally
  • Config keys accessed in settings but not listed in the config spec
  • Events dispatched but not inventoried
  • Error categories defined but not documented

The fidelity validation (Layer 7) only checks raw→clean. This skill checks source→raw — it goes back to the actual source code and verifies that every discoverable user-facing surface was captured in the specs.

When to Run

Run AFTER Layer 3 deep documentation is complete, ideally as part of Gate 1 or as a pre-Gate-1 completeness check. If gaps are found, dispatch deep-dive agents to cover the missing areas before proceeding.

Also run AFTER Layer 7 fidelity validation to catch anything the fidelity check couldn't find (because it was never in the raw specs).

The Checks

Search patterns depend on target shape. For a single-file bundle, grep the bundle directly. For a source tree, grep recursively across the source root. Patterns also depend on the target language's idioms for registering each surface — the examples below give common patterns for several languages; adjust to the actual target.

Check 1: Tool / Command Registration Completeness

Applies to targets that expose a registered command, tool, or handler surface (CLIs with subcommands, plugin hosts, RPC servers with method registration).

Source extraction: grep for the registration pattern used by the target. Examples:

# Named-object pattern (common in JS/TS/Go handler registration)
grep -roE 'name:\s*"[A-Z][a-zA-Z]+"' <source-root> | sort -u

# Decorator-based registration (Python)
grep -roE '@(command|tool|handler|register)\(' <source-root>

# Macro-based registration (Rust)
grep -roE '#\[(command|tool|handler)' <source-root>

# Assigned-constant pattern (JS/TS)
grep -roE 'var [a-zA-Z0-9_]+="[A-Z][a-zA-Z]+"' <source-root> | grep -v 'Exception\|Error\|Element'

Read the full file on GitHub · 188 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. 8d ago First seen · 188 lines · 60 tokens per session scan A b19104e39053

Subscribe to this mod's changes

source-completeness is a skill published in the GitHub repository prime-radiant-inc/greenfield (273 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,955 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 2026-08-30.

Related

Other skills, from other repositories