Skip to content
Back to skills

From Codebase Perspective

ASecurity

Use when asked to answer only from the codebase seat: what existing code tolerates or punishes. Emits a single-perspective analysis without blending. Not for rebuilding from primitives — use from-first-principle. Read-only; no source or remote mutation.

  • 52 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 3, 2026
ai-agents

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 3, 2026

npx -y skills add OutlineDriven/outline-driven-development --skill from-codebase-perspective --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of From Codebase Perspective?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for From Codebase Perspective
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/outlinedriven-from-codebase-perspective-outline-driven-development/badge)](https://www.skillsdirectory.com/skills/outlinedriven-from-codebase-perspective-outline-driven-development)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: from-codebase-perspective
description: 'Use when asked to answer only from the codebase seat: what existing code tolerates or punishes. Emits a single-perspective analysis without blending. Not for rebuilding from primitives — use from-first-principle. Read-only; no source or remote mutation.'
---

# From codebase perspective

## Contract

| Field | Bound contract |
|---|---|
| Trigger | User wants an answer only from the codebase seat (what existing code tolerates or punishes). |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Returns a codebase-perspective analysis in chat. |
| Done | Returns a codebase-perspective answer without blending. |

## Not for

- Rebuilding a design from primitives — use from-first-principle.
- Blended multi-seat analysis — run each from-*-perspective seat independently and compare after.
- Source or remote mutation — this skill is read-only.

## Inputs

The question or proposal to analyze from the codebase seat. The codebase under analysis must be readable in the working tree; if it is not reachable, stop and report that the seat has no evidence.

## Procedure

1. Confirm the seat is codebase only. State that money, customers, timing, impact, career, breaking, rent-seeking, innovation, stability, and moat perspectives are out of scope. Done when: the out-of-scope seats are named.
2. Read the existing code, structure, conventions, and constraints that bear on the question. Done when: the relevant code is read and the evidence base is stated.
3. Determine what the existing code tolerates: patterns, shapes, and directions it already accepts without friction. Done when: tolerates patterns are listed with code evidence.
4. Determine what the existing code punishes: patterns, shapes, and directions that fight the current structure, require rework, or break invariants. Done when: punishes patterns are listed with code evidence.
5. Emit the answer strictly from the codebase seat. Do not blend any other perspective; if another seat is relevant, name it as a separate lens to run independently. Done when: a codebase-perspective answer is emitted without blended content.

## Failure and recovery

- Unreachable codebase: stop. Report that the codebase seat has no evidence and emit no analysis.
- Question outside the codebase seat: stop. Name the seat the question belongs to and emit no codebase answer.
- Pressure to blend lenses mid-answer: refuse. The non-blending rule is load-bearing; comparison happens only after independent outputs.
- Partial evidence: emit only the portion grounded in read code and label the rest as unverified. Never present inference as observed code behavior.

## Output

One codebase-perspective analysis in chat: what the existing code tolerates, what it punishes, and the code evidence for each — no decision selected or recorded; comparison with other lenses happens after their independent outputs.

Files in this skill

  • SKILL.md2.9 KB
  • agents/openai.yaml174 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.