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-panel)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-panel"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-panel/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-panel"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-panel.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 | $0.01150 |
| Opus 5.5 | $0.00000 | $0.00460 |
| Sonnet 5.5 | $0.00000 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
ng-panel 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-panel
Portable command prompt generated from skills/running-a-review-panel/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Convenes several reviewers on one frozen evidence packet, names the diversity axis each seat actually varies, preserves dissent, and verifies every finding against live source before it counts as actionable. Use when a trust-bearing or irreversible verdict currently rests on a single reviewer, or on several that cannot fail differently. Do not use for reversible low-stakes work where a second opinion is ceremony, and do not use it to overrule direct contradictory evidence by majority.
Use when
- A trust-bearing or irreversible verdict -- ship, block, apply-clearance, a security or authorization call -- rests on one reviewer.
- The work is Nuclear / Tier 0, or a Standard change whose blast radius reached a critical system.
- A clean verdict came back on work where a wrong pass is expensive and you cannot name what would have caught the miss.
- Reviewer and actor share a model family, brief, or orchestrator, and you need a check that can fail differently (
docs/02-operating-system/actor-evidence-independence.md). - A consequential plan is about to be locked in and no one has stated the strongest opposing case.
- A prior OPEX record found a review missing a defect another method would have caught.
Do not use when
- The change is reversible and low-consequence. A panel on a Quick change is ceremony.
- You cannot name a second axis to vary. Two seats on one model, brief, and context are one seat; run the single review honestly.
- A deterministic check settles it. A type checker, a test, or reading the source beats four opinions for less.
- A required human gate already settles it. Panels feed gates, never replace them.
- An incident is live and stabilization comes first (use
responding-to-incidents). - You want to overturn direct contradictory evidence. A majority is not a rebuttal.
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.
- 3d ago First seen · 70 lines · 0 tokens per session scan A 835b85d4d06b
ng-panel is a command published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,150 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 2026-10-22.
Other commands, from other repositories
coder-eval-code-review-full
Review the codebase across critical quality axes.
review-pr
Command "review-pr" from saski/arnesto, covering review pr, what this command does, workflow steps, phase 0: initialize review and phase 1: analysis & summary.
review-decide
Resolve a circuit breaker in the review loop. Accepts exactly one argument: approve, reject, or retry.
review_prs
Hold the same bar as reviewpr: a Principal AWS Solutions Architect who is direct, specific, justifies every concern with a concrete risk and a file:line, distinguishes blocking issues from nits, and never rubber-stamps. This command orchestrates that single-PR review across a set of PRs — it does not restate the…
review_pr
Review as a Principal AWS Solutions Architect. You have deep expertise in AWS CDK and TypeScript, serverless and container compute, security/IAM least-privilege, cost, and operational excellence. You hold a high bar: correctness and long-term maintainability over short-term convenience. You are direct, specific, and…
harness-review
Review the current change set from an opposing harness-engineering perspective.