A skill for building and querying a graph of software design records, such as architecture decisions and specifications, plus the source files they govern. It checks how these documents and files are connected.

Use it to validate links, find affected or related documents, trace chains of dependencies, detect orphaned records, detect cycles, and add links inferred from text.

It helps reveal which files or decisions are affected by a change and finds missing, circular, or disconnected links.

graph — Skill for Claude Code and Codex by joestump: A skill for building and querying a graph of…

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/joestump/claude-plugin-sdd/graph

Any agent

npx skills add joestump/claude-plugin-sdd --skill graph

Clone the repo

git clone --depth 1 https://github.com/joestump/claude-plugin-sdd

Made for: Claude Code, Codex.

Or install sdd, the plugin that ships this one along with the rest of its 20 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joestump/claude-plugin-sdd/graph.svg)](https://agentmods.dev/skills/joestump/claude-plugin-sdd/graph)

Your own site

<a href="https://agentmods.dev/skills/joestump/claude-plugin-sdd/graph"><img src="https://agentmods.dev/badge/skills/joestump/claude-plugin-sdd/graph.svg" alt="Measured on agentmods" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,705 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.

Model	Per session	Once invoked
Fable 5	$0.00076	$0.04705
Opus 5	$0.00038	$0.02353
Sonnet 5	$0.00015	$0.00941
Haiku 4.5	$0.00008	$0.00470

Measured 3d ago against content hash d90c069b1176, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graph 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (lib/graph.py), 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/graph/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd:graph — Artifact Graph Skill

Harness portability. This skill runs on any agent harness that loads Agent Skills — Claude Code, Codex CLI, OpenCode, Crush. Tool names used below (AskUserQuestion, Task, TeamCreate, SendMessage, TaskCreate, ToolSearch, mcp__*, ${CLAUDE_PLUGIN_ROOT}) denote capabilities, not hard requirements: map each to your harness's equivalent or use the documented fallback per ${CLAUDE_PLUGIN_ROOT}/references/harness-compat.md. References to CLAUDE.md mean the project memory file (CLAUDE.md, AGENTS.md, or CRUSH.md) per harness-compat § "Project Memory File".

You are running /sdd:graph. This skill builds an in-memory directed graph of the project's ADRs, specs, and governed source files, then answers queries against it.

This skill differs from other SDD skills: instead of orchestrating Claude through markdown instructions, it delegates the deterministic build/validate/traverse work to a Python helper at lib/graph.py in this skill's directory. The output of the helper is the contract — JSON output (Story 6) is the stable shape any future MCP would consume. Markdown is reserved for orchestration and review UX (e.g., the backfill mode's accept/edit/reject in Story 7).

Process

Resolve artifact paths: Follow the Artifact Path Resolution pattern from ${CLAUDE_PLUGIN_ROOT}/references/shared-patterns.md to determine the ADR and spec directories. The resolved ADR directory is {adr-dir} and spec directory is {spec-dir}.

In Story 2 the helper accepts a single root and a single ADR/spec dir per invocation. Workspace-mode aggregation (multiple modules, [module]/ID prefixes) lands in Story 5.
Parse the verb and flags from $ARGUMENTS.

Currently supported: validate, impact <id>, ancestors <id>, chain <id>, orphans, cycles. Backfill (backfill) is recognized at the argparse layer and returns a clear "not yet implemented (planned for Story 7)" message with exit code 2.

Read the full file on GitHub · 317 lines

Files

What ships with it

1 file 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.

lib/graph.py 93 KB runs code

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.

3d ago First seen · 317 lines · 76 tokens per session scan A d90c069b1176

Subscribe to this mod's changes

graph is a skill published in the GitHub repository joestump/claude-plugin-sdd (31 stars, last pushed 15d ago), licensed MIT. It adds 76 tokens to every session and 4,705 once invoked, about $0.0004 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.

Planning canonical-github

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens