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/using-storiesnpx skills add shousper/claude-kit --skill using-storiesgit clone --depth 1 https://github.com/shousper/claude-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shousper/claude-kit/using-stories)<a href="https://agentmods.dev/skills/shousper/claude-kit/using-stories"><img src="https://agentmods.dev/badge/skills/shousper/claude-kit/using-stories.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00105 | $0.00784 |
| Opus 5 | $0.00053 | $0.00392 |
| Sonnet 5 | $0.00021 | $0.00157 |
| Haiku 4.5 | $0.00011 | $0.00078 |
Grade A, and why
using-stories 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Stories
This project runs the story workflow. The board is stories/*.md; the story CLI is the ONLY way to change it.
Rules
- Never hand-edit board or loop files (
stories/**,.claude/story-loop.*.local.md,.claude/story-state.local.json(execution state), learnings, evidence). Every mutation is astorycommand — a hook denies direct writes and names the command to run instead. Do not route around it with Bash. Story loops are per-session: a loop only ever re-prompts the session that started it. doneis evidence- and plan-gated.story donerefuses a story with no## Implementation Planon record (<10 words = thin), runs command gates, and checks review verdicts itself. Never declare a story complete — the CLI decides.- Ready is computed, never stored. Trust
story ready, not file contents or memory. - Park, don't stall. Human-only decision →
story park <id> --question "…", take the next story. Parked questions surface at run end — never bury them. - Discovered work is filed, not done.
story create --discovered-from <id>, then back to the claimed story. - One worktree per story. Claimed work lives in
.worktrees/st-<id>on branchstory/st-<id>. Commit there; never merge to main yourself — integration is the CLI's job. - Budgets are visible and final. The Stop hook shows
iteration N/M. Never restart a stopped loop or edit loop state; a human decides.
CLI quick reference
story ready --json # claim-safe workable set; feedback items first
story claim <id> # claim + create worktree
story show <id> | story board # read views
story update <id> --… [--complexity hard|frontier] # field changes (legal transitions only); absent = routine
story note <id> --body "…" # append an implementation note
story create --title "…" --type <t> [--complexity hard|frontier] [--discovered-from <id>] [--depends-on …] [--touches …]
story park <id> --question "…" # blocked on a human
story record <id> --gate <g> --verdict pass|fail --evidence <path>
story done <id> [--allow-empty] [--allow-unplanned] # gates → plan check → evidence → integrate
story loop status | story loop stop
story doctor [--fix] # board integrity + adoption of hand-written stories
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 · 42 lines · 105 tokens per session scan A d5e233969765
using-stories is a skill published in the GitHub repository shousper/claude-kit (4 stars, last pushed 7d ago), licensed MIT. It adds 105 tokens to every session and 784 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…