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.
npx agentmods add skills/rm2thaddeus/pixel_detective/start-dev-graphnpx skills add rm2thaddeus/Pixel_Detective --skill start-dev-graphgit clone --depth 1 https://github.com/rm2thaddeus/Pixel_DetectiveWhat 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 | $0.00064 | $0.00717 |
| Opus 5 | $0.00032 | $0.00358 |
| Sonnet 5 | $0.00013 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
start-dev-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 2d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start Dev Graph
Use this skill to run Dev Graph locally with the right subset of services.
Quickstart
- Full stack:
powershell -ExecutionPolicy Bypass -File skills\\start-dev-graph\\scripts\\start_dev_graph.ps1 -Mode full - Backend only:
powershell -ExecutionPolicy Bypass -File skills\\start-dev-graph\\scripts\\start_dev_graph.ps1 -Mode backend
Workflow
- Confirm repo root
- Require
developer_graph/api.pyandstart_dev_graph.ps1. - If missing, stop and ask for the correct working directory.
- Decide the requested mode
- full: Neo4j + API + UI
- backend: Neo4j + API only
- services: just Neo4j
- frontend: only Dev Graph UI
- status: report what is running
- stop: stop Docker services and list any remaining processes
- Docker preflight
- Check Docker CLI and Docker Compose:
docker versiondocker compose version
- If Docker is installed but not running, say so and stop.
- Start sequence
- full: run
.\start_dev_graph.ps1 - backend:
docker compose up -d neo4juvicorn developer_graph.api:app --host 0.0.0.0 --port 8080 --reload
- services:
docker compose up -d neo4j
- frontend:
cd tools/dev-graph-uithennpm run dev
When launching uvicorn or npm, use new terminal windows so the main session stays responsive.
- Status checks
docker compose ps- The script prints a port readiness summary (7474/7687/8080/3001).
- Report URLs:
- Stop sequence
docker compose down- Remind the user to close any uvicorn or npm windows still running.
Notes
- Docker Compose service name is
neo4jindocker-compose.yml. - The Windows batch script uses
neo4j_db; do not copy that name here. - Do not redirect uvicorn output to
dev_graph_api.login the repo root. The app writes the same file and will raise a permission error. - The UI may choose port 3001 if 3000 is already in use; the script expects 3001.
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.
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.
- 2d ago First seen · 71 lines · 64 tokens per session scan A 3d262abbe1c8
start-dev-graph is a skill published in the GitHub repository rm2thaddeus/Pixel_Detective (21 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 717 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.