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/techtankto/techtank-site/processnpx skills add techtankto/techtank-site --skill processgit clone --depth 1 https://github.com/techtankto/techtank-siteWhat 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 | $0.00057 | $0.01838 |
| Opus 5 | $0.00028 | $0.00919 |
| Sonnet 5 | $0.00011 | $0.00368 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade A, and why
process 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process
How work is planned and initially built: the sources of truth, how they stay honest with each other, and how milestones are cut and delivered. This skill is the methodology layer and stays project-agnostic; a project's PRD and plan derive their structure from it.
The working loop
Front-loaded on distillation and direction before any build:
Gather inspiration → distill the essence → set direction → design → plan implementation → deliver.
The brief and observations stages of the PRD (§The PRD) are the path toward the design: gathering, distillation, and direction-setting. The design file is the designed solution that path produces, transcribed into the design contract. Planning the implementation lays out the milestone graph (§Milestones) from the PRD and the design.
The PRD
Locate the PRD folder before writing to it. Don't assume a path exists:
check the repo for an existing PRD or docs location first; if one exists but
isn't obvious, ask the user where it lives. If none exists, create docs/prd/.
The PRD lives inside the repo it governs, never in an external notes system:
it's canonical, versioned material (§Division of truth), not a side note.
The PRD folder is the numbered product pipeline, read in order; each stage derives from the ones before it:
| Stage | Owns |
|---|---|
01-brief.md |
The distilled intent: what it is, who it's for, the aesthetic, references |
02-observations.md |
Research and risks, each paired with the direction taken |
03-solution.md |
The settled design at concept level: concept, surfaces, systems |
04-design.md |
The design-token contract, transcribed from the design file |
05-architecture.md |
Stack, information architecture, repo structure, data layer |
06-plan.md |
The plan: the milestone graph (kinds, dependencies), cut from the stages above |
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 · 148 lines · 57 tokens per session scan A bedbc990f108
process is a skill published in the GitHub repository techtankto/techtank-site (5 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 1,838 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 2026-08-31.
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.
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…