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/shousper/claude-kit/plannpx skills add shousper/claude-kit --skill plangit clone --depth 1 https://github.com/shousper/claude-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 | $0.00156 | $0.01304 |
| Opus 5 | $0.00078 | $0.00652 |
| Sonnet 5 | $0.00031 | $0.00261 |
| Haiku 4.5 | $0.00016 | $0.00130 |
Grade A, and why
plan 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Planning
Turn a spec into board data. Each story file is the complete prompt a future worker — with no memory of this conversation — will implement from. Write for that reader.
Core principle: one story = one context window = one PR. Sizing is the whole game; everything else is bookkeeping.
Process
1. Absorb the source
Read the spec or design in full. Unresolved product decisions go back to your human partner (or kit:brainstorming) — never invent them, and never encode an open question as an acceptance criterion. A genuinely open technical question can become a spike story.
2. Decompose
- Epics group related stories: file an epic as its own story whose body carries the shared context; children reference it via
--epic <id>. Epics are never implemented or closed directly — no cascade. - Stories obey the sizing rule. Too big — an "and" in the title, more than one subsystem, more than roughly a day of human work — split it. Two stories that can only ship together — merge them.
3. Draft each story
| Field | Rule |
|---|---|
| title | Imperative and specific: "Add ×N multiplier gates", not "Gates work" |
| type | feature / bug / chore / spike (projects may extend) |
| priority | P0..P3 — P0 means "the board is blocked without it" |
| depends_on | TRUE sequencing only (producer → consumer of an interface). Preference-ordering kills parallelism |
| touches | Coarse globs of what the story will modify, e.g. src/gates/**. A scheduler hint — conservative, directory-level |
| exclusive | true for sweeping refactors that own the whole repo; use it instead of a giant touches list |
| gates | Omit to accept the type defaults from config; override per story (UI story → add visual). Only names defined in .claude/story-workflow.json |
| complexity | routine (default — omit it) | hard for cross-cutting, ambiguous, or multi-subsystem stories | frontier reserved for the rare story your human partner explicitly wants frontier-model planning on. Proposed here, confirmed by the human at the approval gate |
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 · 86 lines · 156 tokens per session scan A f26624551e08
plan is a skill published in the GitHub repository shousper/claude-kit (4 stars, last pushed 6d ago), licensed MIT. It adds 156 tokens to every session and 1,304 once invoked, about $0.0008 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…