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-self-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-self-check)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-self-check"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-self-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 | $0.00000 | $0.00556 |
| Opus 5 | $0.00000 | $0.00278 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
ng-self-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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-self-check
Portable command prompt generated from skills/double-checking-before-acting/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Checks a critical agent action against its exact target, expected result, and stop condition before and after execution. Use when an agent is about to make a critical edit, run a command or migration, use a credential or tool, change a dependency or model, make a public claim, or affect a release. Do not use for low-stakes reversible edits.
Use when
- A command can delete, move, publish, release, migrate, or change something outside the repo.
- An edit touches public claims, where ideas came from, permissions, credentials, dependencies, models, APIs, or the release.
- An agent is about to make a wide or repeated change, where hitting the wrong target is easy.
- A quick candidate is about to become a public claim, an accepted version, or a release action.
Do not use when
- The task is a tiny local edit with obvious proof.
- The action only reads data and has no effect on any later decision.
- The change record already requires a stronger human check before the action.
Inputs
- The action you mean to take, the exact target, the current phase, and where your authority comes from.
- The result you expect, the most likely wrong-target mistake, and when to stop.
- The proof command, review check, or evidence link you will need after the action.
Prompt text
Self-check this Nuclear-grade agent action before it happens.
Inputs:
- packet:
- current phase:
- intended action:
- exact target:
- authority source:
- expected result:
- likely wrong-target or wrong-state error:
- stop condition:
- proof or after-action check:
Return:
- the risky point being checked;
- the action and the target;
- the expected result;
- the stop condition;
- the evidence to collect after the action;
- whether to go ahead, pause, or ask for help.
Verification
- The target is exact enough to rule out work on the wrong file or the wrong environment.
- The expected result is named before the action.
- The after-action check compares the evidence against what you expected.
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 · 60 lines · 0 tokens per session scan A 8f94dbaa710b
ng-self-check 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 556 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
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.
milestone-list
PitWay: List every milestone with a concise one-line status.
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.