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-breakdowngit 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-breakdown)<a href="https://agentmods.dev/commands/flyfission/nuclear-grade-context-engineering/ng-breakdown"><img src="https://agentmods.dev/badge/commands/flyfission/nuclear-grade-context-engineering/ng-breakdown.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 | $0.01095 |
| Opus 5 | $0.00000 | $0.00548 |
| Sonnet 5 | $0.00000 | $0.00219 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
ng-breakdown 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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ng-breakdown
Portable command prompt generated from skills/breaking-down-the-work/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Splits scope into a product-first work breakdown that follows the 100% rule, keeps pieces from overlapping, uses outline numbers, and gives every piece a dictionary entry. Use when an epic, feature, or new subsystem needs a clean split into deliverables, or one source of truth before folders or work begin. Do not use for a one-file edit or a backlog item already broken down.
Use when
- An epic, feature, or new subsystem needs breaking down before planning or layout.
- A folder tree or repo structure is about to be designed and needs a scope basis you can defend.
- Scope keeps growing and no one can say whether the plan is complete or has overlaps.
- Several agents or people need one shared map of the work with no overlaps.
- A
.nuclear/changes/<slug>/packet needs its inside structure decided on principle.
Do not use when
- A single-file or quick edit with an obvious target and no smaller deliverables under it.
- A backlog item that is already broken down, owned, and backed by a dictionary.
- A live incident you have to contain before you stop to reflect.
- The user wants a schedule, a Gantt chart, a cost estimate, or a project-management certification. A work breakdown feeds those, but it is not them.
Inputs
- The end deliverable or goal, stated in one line.
- The mission anchor (
.nuclear/mission.mdor the## Mission anchorinrisk.md) and the charter, when there is one. - Known deliverables, constraints, and any stated non-goals or scope put off for later.
- The existing repo tree and naming conventions, when the work breakdown will be turned into real folders.
templates/standard/wbs.mdwhen you use it.
Prompt text
Build a product-oriented work breakdown (a work breakdown structure, or WBS).
Inputs:
- end deliverable (one line): <the single product or outcome>
- mode: <quick|standard>
- known non-goals / deferred scope: <list or none>
- existing tree to respect: <paths or none>
Do this in order:
1. State the single top deliverable as level 1. If you cannot name one
product, stop and say so: it is a goal, not a deliverable.
2. Break down by product first: split each parent into the parts (nouns) it is
made of, not the actions (verbs) done to it. Keep verbs in a labeled
activity layer only.
3. Apply the 100% rule at every parent: the children must cover exactly the
parent, no more and no less. Write any deferred scope as an explicit gap line.
4. Keep parts separate, with one home each: every part sits under exactly one
parent, and no two siblings overlap. Lift shared work into one common part
rather than duplicating it.
5. Stop splitting at the work-package line: one part that someone can own,
estimate, and verify. A good test is that it takes between about 8 and 80
hours of work (the 8/80 rule), which is usually about 2 to 3 levels deep.
Grade the depth by mode.
6. Number with outline traceability (1, 1.2, 1.2.3).
7. Write the dictionary: for each part give its scope, what is in and out of
scope, the deliverable, the interfaces, how it is accepted, a rough size,
the owner, and its dependencies.
Return: the outline-numbered breakdown table, the dictionary, the named common
parts, the deferred-scope/gap line, and a self-check that it adds up to 100% with
no overlap. Do not produce a schedule, a cost estimate, or a compliance claim.
Then hand off to ng-folders.
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.
- 4d ago First seen · 79 lines · 0 tokens per session scan A e7aea7d916e5
ng-breakdown is a command published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,095 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.
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.
editorial-review-structure
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension.