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-incidentgit 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-incident)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-incident"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-incident.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 | $0.00000 | $0.00606 |
| Opus 5 | $0.00000 | $0.00303 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
ng-incident 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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-incident
Portable command prompt generated from skills/responding-to-incidents/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Runs a live incident the stabilize-first way — name a commander, separate facts from hypotheses, prefer reversible actions, communicate on a cadence, and drive corrective actions to closure. Use when production is broken, data is at risk, or an agent action caused harm. Do not use for routine non-incident work, or as a substitute for the post-incident learning record.
Use when
- Production is down or degraded, data is at risk, security is in question, or users are harmed.
- An agent took a harmful action, or a release is failing its abort criteria.
- Multiple people or agents need one source of truth and one decision-maker during a live event.
Do not use when
- The work is routine and reversible with no live harm (use the normal change path).
- The event is over and the task is the lesson, not the response (use
learning-from-experience). - A standing known problem needs logging, not a live response (use
tracking-deficiencies).
Inputs
- The current symptom, when it started, and what changed just before.
- Who is responding, and who can authorize rollbacks, failovers, or comms.
- The reversible actions available, and the risk of each.
- The channels and the cadence for status updates.
Prompt text
Run this incident the Nuclear-grade stabilize-first way.
Inputs:
- symptom and start time:
- what changed just before:
- responders and who can authorize rollback/failover/comms:
- reversible actions available:
- status channel and cadence:
Return:
- the named commander and the role for each responder
- the safest reversible stabilizing action to take first
- a running timeline with each line labeled fact or hypothesis
- decisions recorded with who made them, reversible-first while the cause is unconfirmed
- the fixed status cadence
- corrective actions, each with an owner and a closure trigger
- the handoff to the post-incident learning and deficiency records
Stabilize first, analyze second. Do not act on an unconfirmed cause with an irreversible fix. Do not imply this is a safety or compliance program.
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.
- 5d ago First seen · 59 lines · 0 tokens per session scan A fb075e47307d
ng-incident is a command published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 606 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.