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-close-packetgit 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-close-packet)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-close-packet"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-close-packet.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 | $0.00873 |
| Opus 5 | $0.00000 | $0.00436 |
| Sonnet 5 | $0.00000 | $0.00175 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
ng-close-packet 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-close-packet
Portable command prompt generated from skills/closing-stale-packets/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Brings an abandoned or half-filled change packet to an honest terminal state by completing it, closing it with a recorded rationale, or deleting it. Use when ng status flags a scaffold or invalid packet, a long session left a draft behind, or work was abandoned mid-packet. Do not use for an actively in-progress packet, or to bypass validation on a packet you intend to ship.
Use when
ng statusreports ascaffoldorinvalidpacket and you are deciding what to do about it.- A long or interrupted session left a packet directory behind that was never finished.
- A packet's underlying change was dropped, superseded, or merged elsewhere, but the packet still sits in
.nuclear/changes/. - A periodic cleanup or release-readiness sweep finds packets that do not map to live work.
- A packet was scaffolded to explore an idea that was then abandoned.
Do not use when
- A packet that is actively being worked right now; it is in progress, not stale.
- A packet you intend to ship: fill and validate it, do not close it to silence the validator.
- Incident containment that must happen before housekeeping.
- The user is asking for formal assurance, certification, or regulatory approval.
Inputs
- The output of
python tools/ng.py status .(packet names, modes, and health tags). - The packet directory under
.nuclear/changes/<slug>and its files. - The originating issue, PR, or mission anchor, to tell whether the change is still live.
- The validator output (
python tools/ng.py validate .nuclear/changes/<slug>) for aninvalidpacket.
Prompt text
Bring a stale Nuclear-grade change packet to an honest terminal state.
Inputs:
- ng status output (packet name, mode, health tag):
- packet path (.nuclear/changes/<slug>):
- originating issue / PR / anchor:
- is the underlying change still wanted? yes / no / unknown:
Do this:
- Establish ownership and intent before acting.
- Choose exactly one terminal state:
- COMPLETE: change is still wanted; fill the prompts that matter, remove the
placeholder marker because the packet is filled, and make validate pass.
- CLOSE: change was deliberately abandoned; add a `NUCLEAR-GRADE-CLOSED:` marker
line with the rationale (why dropped, what replaced it if anything, who decided)
and keep the packet as a record. `ng status` then reports it as `closed`.
- DELETE: it was never a real change (empty scaffold, nothing to learn); remove
the directory so it stops looking like work.
- Prefer CLOSE over DELETE when any rationale is worth preserving.
- Do not fake a pass by deleting the marker on an unfilled packet.
Return the chosen state, the closure note (for CLOSE), and confirmation that
ng status no longer shows an unexplained scaffold or invalid packet.
Do not imply formal assurance, compliance, certification, safety, security, or regulatory adequacy.
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 · 68 lines · 0 tokens per session scan A 7ee5b40ce9d2
ng-close-packet 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 873 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.
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.
validate-prd
Validate an existing PRD against BMAD standards - comprehensive review for completeness, clarity, and quality.