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/baleen37/bstack/story-loopnpx skills add baleen37/bstack --skill story-loopgit clone --depth 1 https://github.com/baleen37/bstackWhat 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 | $0.00031 | $0.01663 |
| Opus 5 | $0.00015 | $0.00831 |
| Sonnet 5 | $0.00006 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
story-loop 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Loop
Drive the current repository to a known-good state. Catalog every externally observable capability as an end-to-end scenario card, then loop through test, fix, and fresh re-test until the results are verified or explicitly parked.
REQUIRED SUB-SKILL: Use e2e-scenario-testing before Phase 0 for the card
format, interface recipes, evidence discipline, and cleanup rules.
Which skill to use
/verify— does one change behave as intended (default path)/e2e-scenario-testing— drive a running app through its real interface, one scenario/story-loop— catalog the whole repository as scenarios, then loop to green
Scope
Use the area or surface named by the user. If the user gives no narrower scope, cover the whole repository.
Derive expected behavior from code, tests, fixtures, schemas, comments, and documentation. Prefer code when sources conflict. Do not guess: record ambiguous, underspecified, unreachable, or externally blocked behavior as an open question in the ledger.
A capability is any externally observable behavior the project exposes, including CLI commands, public library APIs, web routes, API endpoints, background jobs, configuration behavior, authentication flows, data formats, integrations, migrations, plugins, build tools, and developer workflows.
Artifacts
Scenario cards
Create one card per capability under test/scenarios/, named
<area>-<nnn>-<slug>.md. The filename stem is the stable ID; never renumber it.
Use the e2e-scenario-testing card format with these additions:
- Put the actor, the scenario being covered, and source references under What this covers.
- Put code-derived behavior under Expected, with one falsification condition per assertion.
- Put ambiguities and footguns under Sharp edges and in the ledger notes.
Canonical ledger
Maintain exactly one test/scenarios/LEDGER.md:
| ID | Card | Status | Test method | Defect type | Actual result | Notes / open questions |
|---|
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 · 197 lines · 31 tokens per session scan A d92d39ff794d
story-loop is a skill published in the GitHub repository baleen37/bstack (4 stars, last pushed 12d ago), licensed MIT. It adds 31 tokens to every session and 1,663 once invoked, about $0.0002 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.