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-verify-artifactgit 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-verify-artifact)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-verify-artifact"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-verify-artifact.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 | $0.00867 |
| Opus 5 | $0.00000 | $0.00434 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
ng-verify-artifact 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-verify-artifact
Portable command prompt generated from skills/verifying-final-artifacts/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Verifies the delivered artifact a consumer actually receives (a figure, chart, PDF, SVG, screenshot, compiled build, or deployed response) by regenerating it fresh and directly observing the output, not the source that produces it, and ends in one honest verdict. Use when the deliverable is a produced artifact and correctness lives in the rendered result. Do not use for a pure source or code diff with no separate produced output; use reviewing-code-quality instead.
Use when
- The deliverable is a produced artifact a consumer receives directly -- a book or document figure, a generated chart or diagram, a PDF, DOCX, or slide export, a built-UI screen, a compiled binary or app, an exported dataset, or a deployed endpoint's real response.
- An agent has "reviewed" the artifact by reading the source that makes it, and has not itself looked at the output.
- A figure or export keeps getting declared fixed, but the visible defect is still there.
- Correctness of this change lives in how the result renders, paginates, or responds -- not in whether the source is tidy.
Do not use when
- The change is a pure source or code diff with no separate produced output -- use
reviewing-code-qualityinstead. - The claim is textual or non-produced and needs claim-to-evidence mapping rather than a rendered observation -- use
proving-claimsinstead. - A one-line fix where the same freshly regenerated artifact was already observed this pass and nothing downstream of it changed.
Inputs
- The spec or acceptance criteria for the artifact: a reference image, a style guide, the required elements, the expected page count, the expected response shape.
- The current source or generator, and the exact command or tool that produces the artifact.
- A way to actually observe the output at consumer granularity. See
references/observation-recipes.mdfor how to make each artifact type observable.
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 · 62 lines · 0 tokens per session scan A 1ea922f853cd
ng-verify-artifact 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 867 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.