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.
git 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-legal-check)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-legal-check"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-legal-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.
<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-legal-check"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-legal-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00540 |
| Opus 5 | $0.00000 | $0.00270 |
| Sonnet 5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
ng-legal-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 10d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-legal-check
Portable command prompt generated from skills/checking-legal-and-safety-wording/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Reviews public text for license, warranty, compliance, safety, security, certification, and fitness claims that go too far, then rewrites them to stay inside the real limits. Use when shipping or editing public docs, READMEs, or rollout copy. Do not use for internal code comments, or for deciding actual legal fitness, which needs a qualified lawyer.
Use when
- You are editing the README, install docs, public docs, templates, skills, commands, examples, or release notes.
- You are adding source families, assurance-sounding wording, or enterprise rollout wording.
- You are getting the repo ready to be public.
- A public claim needs a self-check before release, or a line that points hard claims to a qualified outside review.
Do not use when
- The work is a private detail with no public-use wording.
- The user needs legal advice; point them to a qualified lawyer.
Inputs
- The changed public text.
LICENSE,DISCLAIMER.md,SECURITY.md, anddocs/00-standards-foundation/compliance-boundaries.md.- The checker's starting list of banned claim phrases.
Prompt text
Run a Nuclear-grade license and assurance-limit check.
Inputs:
- changed public text: <paste/link>
- license/disclaimer files: <links>
- target audience: <user/team/enterprise>
- public trust claims to self-check: <list>
Return:
- whether the MIT license permission stays clear
- wording that keeps the permission to use separate from any assurance claim
- whether each public trust claim is supported, narrowed, or removed
- the unsafe phrases and what to replace them with
- the scan commands to run
- the final limits note
Verification
- Public text says the repo does not create formal assurance, compliance, certification, safety, security, or fitness for regulated use.
- Banned phrases appear only in negative or disclaimer sentences.
python tools/ng.py doctor .passes.
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.
- 10d ago First seen · 54 lines · 0 tokens per session scan A 04fa80d22e58
ng-legal-check is a command published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 540 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
capture-feedback
Quick feedback capture with structured signals.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
verification-repair
PitWay: Bounded, approve-before-edit correction after every task is done.
task-discard
PitWay: Abandon a dispatched task's worktree without integrating.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
milestone-status
PitWay: Show a milestone's status, contract, progress, and tasks.