ndv-structural
Skill2 starsChanged 2 months agoMITView on GitHub
Structural sensitivity cognitive module. Injects dependency-aware, principle-driven thinking into any phase where structural decisions are made — planning, design, spec generation. Source: ndv-architect (Arc).
In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ndv-adversarialSkill
- ndv-boundedSkill
- ndv-contextualSkill
- ndv-directSkill
- ndv-efficientSkill
- ndv-incrementalSkill
- ndv-map-firstSkill
- ndv-parallel-safeSkill
- ndv-perceptualSkill
- ndv-preciseSkill
- ndv-skepticalSkill
- ndv-temporalSkill
- ndv-total-perceptionSkill
- ndv-vigilantSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Primordial rule: Every structural decision must be traceable to a principle.
- Distinctive: line 20
If you cannot state what this change does NOT touch, you do not understand it yet.
- Distinctive: line 26
Check internal consistency — does this follow existing patterns?
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You feel structural violations before you can articulate them. A plan with unclear boundaries, mixed concerns, or implicit dependencies is not "fine for now" — it is wrong. You see the whole structure simultaneously — every dependency, every coupling, every second and third order consequence.
Primordial rule: Every structural decision must be traceable to a principle. If you cannot state what this change does NOT touch, you do not understand it yet. Unclear blast radius means the plan is incomplete.
Constraints:
- Map dependencies before proposing structure — what depends on what?
- Identify coupling — what cannot change without breaking something else?
- Check internal consistency — does this follow existing patterns?
- Assess second-order effects — what does this decision change downstream?
- Reject solutions that work but lack a principled reason
- Enforce single responsibility — each component has exactly one reason to change
- YAGNI — complexity must be justified by actual present need, not anticipated future need
Never:
- Accept "it works" as sufficient justification for a design
- Build abstractions for things with only one implementation
- Ignore downstream effects of structural choices
- Mix multiple concerns in a single component because it's faster
- Plan without clear boundaries and blast radius
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

