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/superhero-tech/super-brain/project-startnpx skills add superhero-tech/super-brain --skill project-startgit clone --depth 1 https://github.com/superhero-tech/super-brainWhat 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 | $0.00048 | $0.01018 |
| Opus 5 | $0.00024 | $0.00509 |
| Sonnet 5 | $0.00010 | $0.00204 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
project-start 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.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Start
Copying three files takes a second. The value of this skill is the conversation that fills them, because a brief nobody pushed back on says "for all users" and "success is more engagement" and helps no one.
Run the interview in the language the human is using.
How to invoke
- "New project", "let's start a project on X"
- Work that has been living in the chat needs a folder
/project-start
How it works
1. Name it
Get the project name, and derive a kebab-case slug: contract-tracker, q3-pricing.
Check 3-Projects/ for a folder with that slug. If it exists, this is an update to an existing project, not a new one - say so and stop.
2. Create the folder
Copy 3-Projects/_template/ to 3-Projects/<slug>/, then create the four working subfolders: discovery/, decisions/, prototypes/, analyses/.
Do not fill in the brief yet.
3. Check what the vault already knows
Read 4-Knowledge/index.md and look for pages that bear on this domain. If there are any, name them:
Before we start: the wiki already has [[Page A]] and [[Page B]] on this. Want me to link them from the brief so you are not starting from zero?
This is the payoff for every source ever ingested. On an empty wiki, skip it without comment.
4. Run the brief interview
One question at a time, in this order. Do not paste the whole template and ask them to fill it in.
| Section | What you are asking for | Push back when |
|---|---|---|
| In one sentence | What it does and for whom | It needs an "and" to hold two ideas - that is usually two projects |
| Who it is for | A segment they could go and find tomorrow | The answer is "everyone", "users", "SMBs" - ask who the first ten would be |
| What done looks like | An outcome with a number and a date | The answer is a direction. "More engagement" is not an outcome; "50 paying by end of Q2, or we stop" is |
| Context | Why this project, why now | It reads as a feature description rather than a reason |
| Constraints | What is genuinely non-negotiable: money, deadline, people, tech, legal | Everything is listed as a constraint, which means nothing is |
| Open questions | What they do not know yet | The list is empty on day one, which means the project has not been thought about |
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 · 83 lines · 48 tokens per session scan A 12144f9102be
project-start is a skill published in the GitHub repository superhero-tech/super-brain (110 stars, last pushed 8d ago), licensed MIT. It adds 48 tokens to every session and 1,018 once invoked, about $0.0002 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.
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.
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.
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…