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/uxname/litestack/full-stack-featurenpx skills add uxname/LiteStack --skill full-stack-featuregit clone --depth 1 https://github.com/uxname/LiteStackWhat 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 | $0.00098 | $0.01019 |
| Opus 5 | $0.00049 | $0.00509 |
| Sonnet 5 | $0.00020 | $0.00204 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
full-stack-feature 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants a feature that touches both the backend and the frontend. This skill is
the conductor: it decides the order, runs the backend side first, syncs the GraphQL
contract, then runs the frontend side. It does not contain backend/frontend logic itself —
it delegates to each sub-project's own instructions (AGENTS.md + its .agents/ files),
which must be followed inside that submodule.
Golden rule: backend first
The frontend generates its GraphQL types from the backend's live schema. If the schema doesn't exist yet, the frontend can't be built correctly. So always: backend → contract sync → frontend.
Process
Step 0: Confirm scope and mode
- Restate the feature in one sentence and confirm both sides are needed.
- Check the operating mode (see root
.agents/OPERATING-MODE.md). It determines where you commit and push at the end.
Step 1: Backend (inside backend/ — Go, liteend-go)
cd backend
Read backend/AGENTS.md first — it routes you to the right file
(backend/.agents/ARCHITECTURE.md covers everything below). The common moves:
- New/changed GraphQL field → edit
internal/graph/schema.graphqls(give every type, field, enum value, input a"description") →task gen→ implement the resolver stub ininternal/graph/resolver/. - DB query → add it to
db/queries/*.sqlwith a-- name:annotation →task gen→ usedatabase.Queries.<Name>. - Schema/column change →
task migration:create name=...(goose, forward-only, embedded). - Background job → define a task type + handler in
internal/queue, register it in the mux. - New REST route → add it in
mountRoutes(internal/app/app.go) AND document it ininternal/devtools/openapi.yaml(a route-sync test enforces this).
Finish the backend side completely and make sure task check passes (Docker-free:
codegen-freshness, build, lint, vuln, format, tidy, secrets).
Step 2: Start the backend so the schema is live
# in backend/ (separate terminal)
task start:dev # brings up Docker db+redis, runs migrations (goose,
# programmatic), GraphQL live at localhost:4000/graphql
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 · 93 lines · 98 tokens per session scan A aeb260680ba4
full-stack-feature is a skill published in the GitHub repository uxname/LiteStack (2 stars, last pushed 10d ago), licensed MIT. It adds 98 tokens to every session and 1,019 once invoked, about $0.0005 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…