Capability Graph Builder

Capability Graph Builder is a skill for Claude Code, Codex from daffy0208/ai-dev-standards. It costs 25 tokens per session (2,831 once invoked), scanned A, original, MIT.

A tool for turning capability descriptions into a searchable map of skills, resources, and what they can do. It uses Codex to infer relationships and check whether declarations agree.

In plain words
What is it for?
Use it after generating manifests to build an orchestration knowledge base, validate relationships, find paths to a goal, or extract capabilities from a particular area.
Why use it?
It makes it easier to discover dependencies and determine which capabilities are needed for a goal instead of checking separate descriptions manually.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/daffy0208/ai-dev-standards/capability-graph-builder
Any agent
npx skills add daffy0208/ai-dev-standards --skill capability-graph-builder
Clone the repo
git clone --depth 1 https://github.com/daffy0208/ai-dev-standards

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Capability Graph Builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/capability-graph-builder.svg)](https://agentmods.dev/skills/daffy0208/ai-dev-standards/capability-graph-builder)
Your own site
<a href="https://agentmods.dev/skills/daffy0208/ai-dev-standards/capability-graph-builder"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/capability-graph-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,831 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.02831
Opus 5 $0.00013 $0.01416
Sonnet 5 $0.00005 $0.00566
Haiku 4.5 $0.00003 $0.00283

Measured 5d ago against content hash ff26be3b269f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Capability Graph Builder 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (build-graph.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/capability-graph-builder/SKILL.md · 434 lines

How it starts

The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capability Graph Builder

Build queryable capability graphs from manifests using Codex for relationship inference

Purpose

Consumes capability manifests (generated by manifest-generator) and constructs a queryable graph structure representing all capabilities and their relationships. Uses OpenAI Codex to infer missing relationships and validate compatibility declarations.

When to Use

  • After generating manifests for skills/MCPs/tools
  • When building the orchestration system's knowledge base
  • To discover capability relationships and dependencies
  • To validate manifest consistency across resources
  • To enable graph-based queries for orchestration planning

Key Capabilities

  • Graph Construction: Builds nodes (capabilities) and edges (relationships) from manifests
  • Relationship Inference: Uses Codex to discover implicit relationships from descriptions
  • Consistency Validation: Validates bidirectional relationships (if A enables B, does B require A?)
  • Path Finding: Supports queries like "what skills are needed to achieve X?"
  • Subgraph Extraction: Finds all capabilities in a domain or with specific effects

Inputs

inputs:
  manifest_dir: string # Directory containing manifest.yaml files (e.g., SKILLS/)
  output_path: string # Where to write capability-graph.json
  validate_consistency: boolean # Run Codex validation on relationships
  infer_missing: boolean # Use Codex to infer missing compatibility fields

Process

Step 1: Scan and Load Manifests

#!/bin/bash
# Find all manifest.yaml files
MANIFESTS=$(find SKILLS MCP-SERVERS TOOLS COMPONENTS INTEGRATIONS -name 'manifest.yaml' 2>/dev/null)

# Load each manifest
echo "Loading manifests..."
for manifest in $MANIFESTS; do
  echo "  - $manifest"
done

Step 2: Build Initial Graph

// Pseudocode for graph construction
const graph = {
  nodes: [],
  edges: [],
  domains: {},
  effects: {}
}

for (const manifest of manifests) {
  // Add node
  graph.nodes.push({
    id: manifest.name,
    kind: manifest.kind,
    description: manifest.description,
    preconditions: manifest.preconditions,
    effects: manifest.effects,
    domains: manifest.domains,
    cost: manifest.cost,
    latency: manifest.latency,
    risk_level: manifest.risk_level
  })

  // Add edges from compatibility
  if (manifest.compatibility) {
    if (manifest.compatibility.requires) {
      for (const required of manifest.compatibility.requires) {
        graph.edges.push({
          from: required,
          to: manifest.name,
          type: 'requires'
        })
      }
    }
    if (manifest.compatibility.enables) {
      for (const enabled of manifest.compatibility.enables) {
        graph.edges.push({
          from: manifest.name,
          to: enabled,
          type: 'enables'
        })
      }
    }
    if (manifest.compatibility.conflicts_with) {
      for (const conflict of manifest.compatibility.conflicts_with) {
        graph.edges.push({
          from: manifest.name,
          to: conflict,
          type: 'conflicts_with'
        })
      }
    }
    if (manifest.compatibility.composes_with) {
      for (const compose of manifest.compatibility.composes_with) {
        graph.edges.push({
          from: manifest.name,
          to: compose,
          type: 'composes_with'
        })
      }
    }
  }

  // Index by domain
  for (const domain of manifest.domains) {
    if (!graph.domains[domain]) graph.domains[domain] = []
    graph.domains[domain].push(manifest.name)
  }

  // Index by effect
  for (const effect of manifest.effects) {
    if (!graph.effects[effect]) graph.effects[effect] = []
    graph.effects[effect].push(manifest.name)
  }
}

Read the full file on GitHub · 434 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago First seen · 434 lines · 25 tokens per session scan A ff26be3b269f

Subscribe to this mod's changes

Capability Graph Builder is a skill published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It adds 25 tokens to every session and 2,831 once invoked, about $0.0001 per session on Opus 5. 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.

Related

Other skills, from other repositories

memory-fabric

Knowledge graph orchestration layer with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting. Unifies search results ranked by recency, relevance, and authority. Use when designing memory retrieval, building entity graphs, or optimizing knowledge graph…

yonatangross/orchestkit · 61 tokens

dale-graph

Synthesize and run a unique graph of visible Codex tasks, each able to orchestrate its own bounded node-local subagents, directly from the current request, repository boundaries, dependencies, evidence needs, and runtime discoveries. Use when the user invokes $dale-graph, selects Dale Graph through /skills, explicitly…

lubluniky/dale · 100 tokens

dale-max

Run a maximum-assurance resident-worker orchestration loop with persistent forked Codex threads, thread-local task-derived subagents, plan review, synthesis, an explicit pass gate, and progress-gated revision feedback without preset cost, token, reviewer-count, or cycle budgets. Use only when the user explicitly…

lubluniky/dale · 96 tokens

dale-coach

Review recent Codex task history through one or two visible GPT-5.6 Luna Max coach tasks and return evidence-backed advice about prompting, model and skill selection, delegation, authority, validation, and workflow efficiency. Use when the user explicitly invokes $dale-coach, selects Dale Coach through /skills, or…

lubluniky/dale · 104 tokens

dale-proof

Verify an existing implementation, fix, migration, deployment, runtime behavior, compatibility boundary, or other technical claim by mapping atomic claims to direct, fresh, reproducible primary signals and returning scoped PROVEN, PARTIAL, UNPROVEN, or CONTRADICTED verdicts with a compact proof capsule. Use when the…

lubluniky/dale · 127 tokens

dale-lenses

Reframe an already bounded, difficult engineering, product, operational, or strategic question through one rigorous reasoning lens and at most one genuinely opposing lens, producing a falsifiable model, decision cruxes, and evidence needs instead of a tour of frameworks. Use when the user explicitly invokes…

lubluniky/dale · 135 tokens