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-deficiency)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-deficiency"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-deficiency/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-deficiency"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-deficiency.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 | $0.00621 |
| Opus 5.5 | $0.00000 | $0.00248 |
| Sonnet 5.5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
ng-deficiency 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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-deficiency
Portable command prompt generated from skills/tracking-deficiencies/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Keeps a standing register of known deficiencies so flaky tests, noisy alerts, unowned services, and recurring incidents get aged, owned, and fixed or formally risk-accepted instead of quietly normalized. Use when a known problem will outlive a single change. Do not use for a one-off lesson already closed inside a packet, or for brand-new work with no accepted deficiency yet.
Use when
- A known problem will outlive the current change: a flaky test, a noisy alert, an unowned service, a dead dashboard, a recurring incident, or deferred hardening.
- A review or incident surfaced something real that is not being fixed right now.
- You want to convert "we all know about that" into an owned, dated, decided entry.
Do not use when
- A lesson is already fully closed inside a packet and needs no standing tracking.
- The work is brand-new and has no accepted deficiency yet (rate it as a normal change instead).
- The item is an active incident needing response, not logging (use
responding-to-incidents).
Inputs
- The deficiency, where it shows up, and how it was found.
- Its consequence and how often it bites.
- Who could own it, and whether a fix or a formal risk-acceptance is the right disposition.
- Any related incident, OPEX lesson, or controlled item.
Prompt text
Log this deficiency the Nuclear-grade way.
Inputs:
- deficiency and where it shows up:
- how it was found:
- consequence and frequency:
- candidate owner:
- related incident / OPEX / controlled item:
Return:
- a one-line description with a link to where it shows up
- the date first seen, so its age is visible
- the assigned owner (an unowned deficiency is itself a finding)
- the disposition: fix by a date, or formally accept the risk with a named owner and a revisit date
- the review trigger so an accepted risk does not become permanent by default
- links to related incident, OPEX, and controlled-item records
Decide fix-or-accept; never leave it as a silent "known issue." Do not imply formal assurance.
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.
- 1mo ago First seen · 58 lines · 0 tokens per session scan A 8eee7d2055f7
ng-deficiency 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 621 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
backlog
PitWay: Capture out-of-scope work discovered mid-task, without expanding current scope.
cooldown
Close out a cycle — invoke cooldown-report and finalize the active pitch's bet status.
feature-track-init
Initialize Feature Track in this repository.
hill
Update a scope's status on the hill chart of the active pitch.
retro
Run a structured retrospective for the current session. Proposes rule and documentation changes but does not apply them.
work
Work unit management: list, continue, checkpoint, switch.