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.
npx agentmods add commands/flyfission/nuclear-grade-context-engineering/ng-trust-checkgit clone --depth 1 https://github.com/FlyFission/nuclear-grade-context-engineeringWrote 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.
[](https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-trust-check)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-trust-check"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-trust-check.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00645 |
| Opus 5 | $0.00000 | $0.00322 |
| Sonnet 5 | $0.00000 | $0.00129 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
ng-trust-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-trust-check
Portable command prompt generated from skills/vetting-outside-code-and-models/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Checks dependencies, models, APIs, SaaS tools, generated files, and vendor claims against how you will actually use them, the proof you have, the gaps, and the release impact. Use when any of these affect evidence, permissions, data, releases, or public trust. Do not use for an internal cleanup with no outside dependency, or for a does-it-work question.
Use when
- A change adds or updates a package, a model, an API, an online service, a generated file, a build service, or a data source.
- You are leaning on an outside claim as proof of behavior, security, privacy, reliability, licensing, or release readiness.
- A tool gets credentials, network access, data access, or a say in releases.
Do not use when
- The dependency is for development only, easy to undo, and already covered by a quick proof.
- The request is only to cite a public source, not to lean on it as trust evidence.
- A qualified security or purchasing review is needed, which happens outside this repo.
Inputs
- The dependency, model, API, or tool: its name, version, provider, intended use, which controlled items it touches, and the critical characteristics your use relies on.
- The vendor or source claims, the evidence you saw yourself, the backup controls, and what would force a re-check.
- The effects on data, credentials, permissions, the build, the release, and public claims.
Prompt text
Check Nuclear-grade dependency/model/API trust.
Inputs:
- packet:
- external item:
- provider/source:
- version/model/API surface:
- intended use:
- critical characteristics your use relies on:
- consequence if wrong/unavailable/compromised/changed:
- data/credential/permission/network impact:
- vendor/source claims:
- acceptance method per characteristic + repo-observed evidence + who verified:
- compensating controls:
- revalidation trigger:
Keep the outside claims separate from your local evidence. Return a decision for how you intend to use it, the critical characteristics and the acceptance method that verified each, the gaps (a characteristic you cannot verify blocks acceptance), the controls that make up for them, the effect on the release, and whether to ship, defer, block, or require a qualified review.
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.
- 6d ago First seen · 56 lines · 0 tokens per session scan A 14de123927cb
ng-trust-check is a command published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 645 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.
Other commands, from other repositories
coder-eval-implement-plan
Implement an approved codereval plan phase by phase with risk-scaled per-phase review, then a final code review.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
fix
Universal debugging and fix application with semantic code analysis.
status-enhanced
/forge:status-enhanced is the heavyweight sibling of /forge:status. While the standard status command gives you a quick overview, the enhanced version runs a full seven-source analysis: complete git history with a 7-day commit activity heatmap, full test suite execution with verbose output, TypeScript compilation…
domain-research
Conduct domain research covering industry analysis, regulations, technology trends, and ecosystem dynamics using current web data and verified sources.