Skip to content
CAI
Software that uses CAICheck a score

MakFly/superpowers-symfony

49.2

Weak · 21 September 2026

1k

lines of production code

TypeScript

primary language

4

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

This system is a configuration and tooling library designed to integrate Symfony-based projects with various AI coding assistants. It provides a centralized build pipeline that generates harness-specific rules, prompts, and context files for tools like Cursor, Copilot, and Codex from a single source of truth. Additionally, it includes scripts to detect project environments and output structured context data to help AI agents adapt to the specific setup.

Features

Add harness-agnostic context detection and generated distribution files for AI coding agents

The library now includes a \bin/symfony-context\ shell script that automatically detects the Symfony version, API Platform presence, Docker environment, and test framework, outputting the result in JSON, Markdown, or environment-variable formats to help coding agents adapt to the project setup. Additionally, the \dist/\ directory now contains generated files tailored for various AI coding assistants—including Codex, Cursor, Windsurf, GitHub Copilot, Gemini, aider, and OpenCode—providing the necessary prompts, rules, and instructions to integrate the Symfony skill library into those specific tools.

bin, dist · high confidence

New harness-agnostic build system for AI coding assistants

The repository now uses a centralized build pipeline (scripts/build.ts) to generate tool-specific configuration files from a single source of truth in content/. This replaces the previous manual maintenance of indexes and harness-specific files, automatically producing rules for Cursor, Windsurf, and GitHub Copilot, prompts for Codex CLI and Gemini CLI, agent definitions for OpenCode and aider, and a neutral AGENTS.md index for Grok Build and others. The new system also includes a content linter (lint\_skill\_content.ts) to enforce skill structure and a comprehensive validator (validate.ts) to ensure data integrity and prevent vendor-specific terms from leaking into portable content.

scripts · high confidence

Behavioural changes

Simplified session-start hook output format

The session-start hook now outputs plain Markdown instead of a JSON object, resolving a schema validation bug where unknown JSON keys prevented context from reaching the model. The script has been refactored into a thin wrapper around a harness-agnostic context generator, removing the previous inline logic for detecting Symfony versions, API Platform, Docker types, and test frameworks.

hooks · high confidence

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

This is the PUBLIC form of this artifact. Findings are listed in full, but the details of SECURITY findings — which rule fired, in which file, on which line, and how to fix it — are deliberately withheld, and any secret-scanner results are excluded entirely. Where detail is absent here it was REMOVED FOR PUBLICATION; it is not missing from the analysis. The complete artifact is available from the repository owner.

Score

  • CAI 51 → 49 (-1.6)
  • Rubric changed (rubric-2026.08.19 → rubric-2026.09.15) — scores are not directly comparable.

Lenses

  • Code Health 100 → 61 (-38.9)
  • Architecture 69 → 69 (+0.0)
  • Maturity 60 → 57 (-2.8)
  • Readiness 30 → 34 (+3.9)
  • Security 71 → 94 (+22.9)

Resolved (10)

  • Dependency hygiene not measured — no supported dependency manifest was read
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • LLM evaluation failed
  • No exposed public API
  • early-stage repository — too few commits for a meaningful bus factor
  • early-stage repository — too little history to judge knowledge freshness

New (24)

  • Dependency hygiene PARTLY measured — npm pinning read, dependency currency not (the committed lockfile resolved no direct production dependency)
  • Documentation: no installation or build instructions (README.md)
  • Documentation: no usage examples (README.md)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • Medium: security finding (details withheld)
  • Medium: security finding (details withheld)
  • Medium: security finding (details withheld)
  • No dependency advisory monitoring
  • Rotate the exposed credentials — git history can't be un-committed
  • Secret: generic-api-key (.env)
  • validate.validateClaudeCode (cognitive 37) (scripts/validate.ts)
  • …and 4 more

Changes since last survey

  • 4 commits — 3 feature/other, 1 fixes

By area

  • (root) — 1 commit
  • .github/workflows — 1 commit
  • content/skills — 1 commit
  • skills/quality-checks — 1 commit

Notable commits

  • fix: fix(ci): keep the link check from failing on files with no relative links
  • change: Fix formatting of description in SKILL.md (#12)
  • change: chore: update repository URLs after transfer to dev-toolings
  • change: feat: make the library harness-agnostic

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

MakFly/superpowers-symfony was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 21 September 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit ab84bcb7561060acd5b210d9ad5632289edcc0cc — the exact code this score is about.
  • Scored under rubric-2026.09.15 — the same rubric and the same method as every other entry in this index.
  • Measured by watchdog.canine.dev using codehealth-analyzer preprod-b84573e22831.