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/techymt/claude-code-superpowers/state-managementnpx skills add TechyMT/claude-code-superpowers --skill state-managementgit clone --depth 1 https://github.com/TechyMT/claude-code-superpowersWhat 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 | $0.00064 | $0.01508 |
| Opus 5 | $0.00032 | $0.00754 |
| Sonnet 5 | $0.00013 | $0.00302 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
state-management 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State Management
The pattern
Shared mutable state is wrapped in a deep-immutable type. Direct mutation is a compile error. All updates go through a single setter that accepts a pure function (prev: State) => State. Returning the same reference signals "nothing changed" and skips downstream work — no re-render, no diff.
The reducer function is atomic: the entire state object is replaced in one operation. Partial updates are expressed as spreads — the fields that didn't change carry forward from prev; only the changed fields are new values. This makes every transition explicit, traceable, and race-condition-safe.
Why this matters
Claude Code's AppState is a large object — UI flags, permission context, task records, session configuration — shared across tools running concurrently, React components rendering in a terminal, and background task workers. Without an immutability contract, a tool updating tasks could race with a UI component reading toolPermissionContext mid-update, producing torn reads.
The DeepImmutable<T> wrapper makes that impossible at the type level. TypeScript rejects direct assignment to any nested field. The only way to change state is through the reducer, which replaces the entire object atomically. The reference-equality short-circuit (return prev when nothing changed) prevents the scheduler from scheduling re-renders for no-op updates — important when multiple tasks call setAppState in rapid succession.
How to apply it
- Read state via
context.getAppState()— this returns the current immutable snapshot. - Write state via
context.setAppState(prev => next). Always return a new object; never mutateprev. - For nested updates (e.g. a field inside
tasks), spread at every level:{ ...prev, tasks: { ...prev.tasks, [id]: updated } }. - When the update is conditional and the condition is false, return
prevunchanged — this is the reference-equality no-op signal. - For repeated nested updates to the same sub-object, extract a helper that handles the spread and the no-op check — if the updater returns the same reference, return
prevunchanged to avoid triggering subscribers unnecessarily. - Never access state from module-level variables. State always comes from
context.getAppState().
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 · 151 lines · 64 tokens per session scan A f7757fa0a9c4
state-management is a skill published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 1,508 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…