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/whitequeen306/code-cortex-loop/edge-case-and-state-analysisnpx skills add whitequeen306/code-cortex-loop --skill edge-case-and-state-analysisgit clone --depth 1 https://github.com/whitequeen306/code-cortex-loopWhat 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 | $0.00036 | $0.00937 |
| Opus 5 | $0.00018 | $0.00468 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
edge-case-and-state-analysis 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edge Case & State Analysis (Deep)
Auxiliary depth skill for passes 1 (correctness), 3 (tests), 4 (errorHandling). Pair with the pass domain skill.
Go deep on triggers and state. This skill finds how bugs happen — your pass contract decides how to score them (logic bug vs missing test vs silent failure).
When to apply
- Branching, flags, enums, status fields
- Retries, queues, webhooks, async callbacks
- Caching, invalidation, read-your-writes
- Permissions/roles checked then used later (timing)
- Batch, pagination, cursor, streaming
- Init/shutdown, subscribe/unsubscribe
Depth checklist
Boundary inputs
| Class | Examples to trace |
|---|---|
| Empty | [], {}, "", no rows, first page empty |
| Extremes | max length, max int, zero quantity, negative where unsigned expected |
| Missing | optional field absent vs null vs undefined vs wrong type |
| Duplicate | double click, replayed idempotency key, duplicate message |
| Malformed | parse succeeds but semantic garbage reaches logic |
Respect validation: don't invent states ruled out upstream unless you prove validator bypass.
State machines
- Draw states and transitions mentally or inline in finding
- Impossible state reachable? (PAID + CANCELLED)
- Skipped transition? (DRAFT → SHIPPED without PAY)
- Terminal state re-entered?
- Stale flag after async gap
Idempotency & duplication
- Same request twice — same outcome or corrupt?
- Webhook redelivery, at-least-once queue consumption
- Client retry after timeout — server already applied?
Ordering & races
- Response B arrives before A; UI or handler assumes order
- Delete during fetch; update during delete
- Cache read between write and invalidate
- check-then-act without lock
Concurrency
- Shared map/array mutated from parallel tasks
- Non-atomic read-modify-write on counter/balance
- Timer/interval not cleared; listener leak changes behavior over time
Partial failure
- 3 of 10 items succeed — what's the aggregate state?
- Rollback partial? Compensation? User sees what?
- Cancel mid-flight — resources cleaned?
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 · 136 lines · 36 tokens per session scan A 985c48bcff44
edge-case-and-state-analysis is a skill published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 937 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 2026-08-30.
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.