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/abstractonion/cadence/loopnpx skills add abstractonion/cadence --skill loopgit clone --depth 1 https://github.com/abstractonion/cadenceWhat 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 | $0.00033 | $0.00507 |
| Opus 5 | $0.00016 | $0.00253 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
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.
What it actually says
The Engineering Loop
Every non-trivial change moves through seven phases. Skipping a phase is a choice — name which one and why.
- Think — restate the problem before touching code. Who is this actually for? What's the smallest version that delivers value? What is the user already doing as a workaround? See
propose-then-implement. - Plan — pick an approach with eyes open. Note data flow, edge cases, failure modes, and the tests that would prove it works. Surface hidden assumptions instead of guessing past them. See
scope-and-dispatchfor parent routing before subagent fan-out. Single-thread decomposition:break-work-into-verifiable-stepsor/plan. Multi-workstream coordination (disjoint scopes, explicit dependencies): delegate tocadence-planner, then partition fan-out perparallel-workstreams. - Build — implement with the smallest diff that cleanly expresses the change. Don't refactor adjacent code unless the structural fix is the whole point.
- Review — read your own diff like a stranger before handing it off. See
self-review-before-handoff. - Test — verify against reality, not intent. Return the evidence bundle per
verify-with-runtime(library:test_name+ red/green output; UI: flow + console; API/CLI:exit_code+ output; blocked:blocked_reason). Stale evidence from earlier in the session does not count. - Ship — clean commits, accurate description, fresh evidence at the moment of push. See
clean-commits. When a PR already exists for this branch, hand off ongoing settle to/own-pr(cadence-own-pr) instead of a one-shot push-and-exit. - Reflect — name one durable lesson before moving on. See
capture-learnings.
When a bug shows up, the loop is the same — Think (what is actually happening?) → Plan (one hypothesis at a time) → Build (smallest fix) → Review/Test/Ship/Reflect. See investigate-before-fixing for the bug-specific gates.
The cost of doing the complete thing is much lower than it used to be. Default to it.
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 · 21 lines · 33 tokens per session scan A 12767a74cc80
loop is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 507 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.
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…