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/jlong/quiddity/q-setupnpx skills add jlong/quiddity --skill q-setupgit clone --depth 1 https://github.com/jlong/quiddityWhat 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 | $0.00040 | $0.00609 |
| Opus 5 | $0.00020 | $0.00304 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
q-setup 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/q-setup
You are running the full Quiddity setup flow for the user's project. This will discover their process and tools, then generate all three build-loop skills.
Process
-
Welcome the user. Briefly explain what Quiddity does: it will scan their project, learn about their development process and tools, set up CLIs and MCPs, then generate three custom skills (
/new-issue,/next-task,/approve) tailored to their project. -
Run /q-scan-project to scan the project structure. This documents key files, tech stack, conventions, and project layout in
.quiddity/project.md. -
Run /q-which-process to discover the user's SDLC. This captures their branching strategy, code review process, issue workflow, and other conventions in
.quiddity/process.md. It can referenceproject.mdfor context. -
Run /q-which-tools with all categories needed across the three skills:
/q-which-tools issues source-control ci prBecause
/q-which-processhas already run,/q-which-toolscan reference.quiddity/process.mdto pre-fill answers and ask smarter questions. -
Run /q-setup-tools to walk through CLI and MCP setup for each tool discovered in the previous step. This checks what's already installed and helps set up anything missing.
-
Run /q-setup-new-issue to generate the
/new-issueskill. Since project.md, process.md, and tools.json are already populated, this will skip the interviews and go straight to skill-specific questions. -
Run /q-setup-next-task to generate the
/next-taskskill. -
Run /q-setup-approve to generate the
/approveskill. -
Summarize. Show the user what was generated:
- The location of
.quiddity/project.md,.quiddity/process.md, and.quiddity/tools.json - The three generated skills and their locations
- A quick reminder of how to use each skill:
/new-issue [description]— create a new issue/next-task— pick up and implement the next task/approve [pr-number]— merge an approved PR
- Suggest they review each generated skill and tweak as needed
- Remind them to commit
.quiddity/and the generated skills to source control so the whole team shares the same configuration
- The location of
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 · 54 lines · 40 tokens per session scan A efb2ea16c1a9
q-setup is a skill published in the GitHub repository jlong/quiddity (5 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 609 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 2026-08-31.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…