Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

AI Mistake Prevention — Failure modes to avoid on every task:

• Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal.
• Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing.
• Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain.
• Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path.
• When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site.
• Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code.
• Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks.
• Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis.
• Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly.
• Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Connect API

Detect frontend HTTP calls and match them to backend route definitions, creating

API_ENDPOINT

How It Works

The connector scans frontend files for HTTP calls and backend files for route definitions, normalizes URL paths, and matches them using a multi-strategy algorithm:

1. Exact match — normalized paths identical
2. Prefix-augmented — prepends

   routePrefix

   to frontend path
3. Suffix match — strips

   routePrefix

   from backend, matches remainder
4. Deep strip — strips leading

   {param}

   segments from backend (handles class-level

   {companyId}

   routes)
5. Controller resolution — resolves .NET

   [controller]

   placeholder to actual class name

Zero-Config Auto-Detection

No configuration needed. The connector auto-detects frameworks by scanning for marker files:

angular.json

nx.json

@angular/core

react

vue.config.js

vue

next.config.js

next

svelte.config.js

svelte

*.csproj

Microsoft.AspNetCore

pom.xml

build.gradle

spring-boot

express

@nestjs/core

fastapi

manage.py

Gemfile

rails

go.mod

Auto-Run Behavior

The connector runs automatically in these situations:

build

update

sync

_auto_connect()

trace

query

connections

_ensure_connectors_ran()

You almost never need to run this manually. The graph CLI handles it automatically.

Custom Config (Optional)

For projects with custom HTTP patterns (e.g., base class API service), add to

docs/project-config.json

{
    "graphConnectors": {
        "apiEndpoints": {
            "enabled": true,
            "frontend": {
                "framework": "angular",
                "paths": ["src/app/"],
                "customPatterns": ["this\\.\\s*(get|post|put|delete|patch)\\s*[<(]\\s*['\"]([^\"']+)"]
            },
            "backend": {
                "framework": "dotnet",
                "paths": ["src/Api/Controllers/"],
                "routePrefix": "api",
                "customPatterns": []
            }
        }
    }
}

Custom patterns extend (not replace) built-in framework patterns. Explicit config overrides auto-detected config for paths.

Manual Run

python .claude/scripts/code_graph connect-api --json

Steps (when manually invoked)

1. Run connector via Bash:

   python .claude/scripts/code_graph connect-api --json
   

2. Report results: Frontend calls found, backend routes found, matches created, edge count

Matching Strategies

The connector tries 5 strategies in order (highest confidence first):

/api/users

/api/users

/users

api

/api/users

/api/users

/users

/users

/api/{param}/users

/users

/users

{param}

See Also

• Implicit Connections — For event buses, entity events:

  graphConnectors.implicitConnections[]

  in project-config.json. CLI:

  connect-implicit --json

Related Skills

• /graph-build

  — Build/update the knowledge graph (prerequisite)

• /graph-trace

  — Trace full system flow (API_ENDPOINT edges enable frontend-to-backend tracing)

• /graph-blast-radius

  — Analyze structural impact of changes

• /graph-query

  — Query code relationships in the graph

Closing Reminders

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using

  TaskCreate

  BEFORE starting
• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
• MANDATORY IMPORTANT MUST ATTENTION cite

  file:line

  evidence for every claim (confidence >80% to act)
• MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality <!-- SYNC:critical-thinking-mindset:reminder -->
• MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact. <!-- /SYNC:critical-thinking-mindset:reminder --> <!-- SYNC:ai-mistake-prevention:reminder -->
• MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction. <!-- /SYNC:ai-mistake-prevention:reminder -->