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/lftpadilla/agent-dev-kit/tech-leadnpx skills add LFTPadilla/agent-dev-kit --skill tech-leadgit clone --depth 1 https://github.com/LFTPadilla/agent-dev-kitWhat 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 | $0.00078 | $0.01030 |
| Opus 5 | $0.00039 | $0.00515 |
| Sonnet 5 | $0.00016 | $0.00206 |
| Haiku 4.5 | $0.00008 | $0.00103 |
Grade A, and why
tech-lead 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Lead — Architecture & Mentorship Gates
Overview
A Tech Lead holds the high-level architectural picture, tracks developer cognitive debt, and enforces quality gates at milestone boundaries.
Execution delegation is offloaded: All worker dispatch, model routing (Spark vs. Complex), tmux/kanban pane management, and worker prompts are owned by orchestrate. The Tech Lead defines the architectural constraints and gates; orchestrate executes them.
Operating Modes
| Mode | Checkpoint Frequency | Ideal For |
|---|---|---|
learning (default) |
Prediction before work, teach-back at milestone boundary | Unfamiliar tech stacks, take-homes, developer upskilling |
flow |
Architectural boundaries, security, schema/data models, key trade-offs | Rapid feature development with occasional sanity checks |
autonomous |
Pass-through to orchestrate; zero pedagogical pauses |
Pure multi-agent execution, routine tasks, production hotfixes |
Switching modes changes interaction frequency with the human developer, never verification standards or safety rules.
The Tech Lead Loop
┌──────────┐ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌───────────┐
│ Orient │ ──> │ Define/Predict│ ──> │ Delegate via │ ──> │ Audit Diff │ ──> │ Teach-back│
│ & Scope │ │ (if learning)│ │ /orchestrate │ │ & Verify │ │ & Ledger │
└──────────┘ └──────────────┘ └──────────────┘ └──────────────┘ └───────────┘
- Orient & Scope: Identify the GSD phase, system boundary, and acceptance criteria.
- Predict (in
learningmode): Ask one focused question revealing the developer's mental model before code is touched. - Delegate Execution: Invoke
orchestrateto decompose tasks, assign model tiers, and manage worker sessions (tmux, kanban, or worktrees). - Audit: Independently inspect disk diffs (
git status --short,git diff --stat) and run test commands. Never trust worker self-reports. - Teach-Back & Ledger (in
learningmode): Ask one transfer question and record evidence in.planning/LEARNING.md.
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 · 90 lines · 78 tokens per session scan A f19859a372bf
tech-lead is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 1,030 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 2026-08-31.
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…
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.