ng-source-check

ng-source-check is a command for coding agents from FlyFission/nuclear-grade-context-engineering. It costs 0 tokens per session (537 once invoked), scanned A, original, MIT.

A command that checks whether public writing makes honest claims about outside sources such as standards, agencies, frameworks, or borrowed ideas.

In plain words
What is it for?
Use it when reviewing source citations and public claims in documentation, templates, skills, change records, or release text.
Why use it?
It helps prevent documentation from overstating what a source proves, or implying certification, compliance, or approval without evidence.

Command

Part of the nuclear-grade plugin — 24 skills, 28 commands, 5 agents shipped together

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 commands/flyfission/nuclear-grade-context-engineering/ng-source-check
Clone the repo
git clone --depth 1 https://github.com/FlyFission/nuclear-grade-context-engineering

Or install nuclear-grade, the plugin that ships this one along with the rest of its 24 skills, 28 commands, 5 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 ng-source-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-source-check.svg)](https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-source-check)
Your own site
<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-source-check"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-source-check.svg" alt="Measured on agentmods" 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 537 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 $0.00000 $0.00537
Opus 5 $0.00000 $0.00269
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00054

Measured 3d ago against content hash db8c1b57252d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ng-source-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 3d 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/ng-source-check.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ng-source-check

Portable command prompt generated from skills/checking-source-claims/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.

Checks that the way you cite source families, agencies, standards, or borrowed ideas is honest and does not claim too much. Use when public docs, templates, skills, change records, or rollout copy point to outside sources. Do not use for private notes, or for checking whether code actually works.

Use when

  • A doc, template, skill, command, or change record cites a source family.
  • New standards, frameworks, agencies, or assurance-sounding terms show up.
  • A public claim might sound like compliance, certification, approval, or formal verification.
  • A dependency, model, API, or vendor claim might get confused with proof from your own repo.

Do not use when

  • The change is private code with no method claim and no source claim.
  • A source cannot be made public; use private, project-specific controls outside this public repo.

Inputs

  • The changed public text.
  • docs/00-standards-foundation/source-map.md.
  • docs/01-field-guide/source-to-concept-crosswalk.md.
  • docs/00-standards-foundation/compliance-boundaries.md.

Prompt text

Run a Nuclear-grade source-lineage check (where the ideas come from).

Inputs:
- changed public text: <paste/link>
- cited source families: <list>
- source-map rows: <links>
- source or vendor claims used as evidence: <list>

Return:
- a status for each source: verified-public, supporting-context, public-url-needed, or excluded-direct
- the difference between an influence, a source's claim, local proof, a requirement, and an authority
- the wording changes needed so you make no claim of compliance or approval
- the source-map or crosswalk updates
- the validation and scan commands

Verification

  • Source claims point to source-map.md or to public URLs.
  • Public docs never present an unconfirmed source as direct lineage.
  • Scans for the boundary phrases find them only in negative or disclaimer sentences.

Read the full file on GitHub · 54 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. 3d ago First seen · 54 lines · 0 tokens per session scan A db8c1b57252d

Subscribe to this mod's changes

ng-source-check is a command published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 537 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 2026-08-30.