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/lightninglabs/wavelength/context-lifecyclenpx skills add lightninglabs/wavelength --skill context-lifecyclegit clone --depth 1 https://github.com/lightninglabs/wavelengthWhat 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 | $0.00053 | $0.01585 |
| Opus 5 | $0.00026 | $0.00792 |
| Sonnet 5 | $0.00011 | $0.00317 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
context-lifecycle 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Lifecycle Review
Use this skill to catch async work that accidentally captures a short-lived caller context.
The failure mode is subtle: ctx is usually the nearest variable, so a
goroutine, timer, callback, or actor handoff may inherit an RPC/test/request
context even though the work must continue after that caller returns. When the
caller exits, the context is cancelled and the background work can silently stop
too early.
Core Question
For every asynchronous handoff, ask:
Who owns this work, and when should it stop?
The answer determines which context is correct.
Search
Start with targeted searches instead of reading whole packages:
rg -n 'go func|AfterFunc|time\.AfterFunc|context\.AfterFunc' \
--glob '*.go' [path]
rg -n 'Done\(|WithCancel\(|WithTimeout\(|WithDeadline\(' \
--glob '*.go' [path]
rg -n '\.Tell\(|\.Ask\(|Register|Subscribe' \
--glob '*.go' [path]
Then inspect each hit in context.
Classify The Owner
Classify each async handoff before suggesting a fix.
Caller-Owned Work
The caller waits for the goroutine before returning, or the goroutine only performs request-scoped work.
Using the caller context is usually correct.
Examples:
- a goroutine joined by
WaitGroup.Waitbefore return - a worker that sends one result and the function waits on that result
- a helper that should abort when the RPC deadline expires
Component-Owned Work
The work is started by a caller but owned by a daemon, wallet, actor, or service after startup.
Do not capture the RPC/request context. Use a component root context, a registration-owned context, or an explicit context with its own cancel path.
Examples:
- wallet sync loops started by
UnlockWallet - daemon background workers started from an RPC
- actor goroutines started during actor construction
- server connection runtimes started by daemon setup
Registration-Owned Work
The work forwards notifications until an explicit returned Cancel, Stop, or
subscription teardown is invoked.
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 · 231 lines · 53 tokens per session scan A 803d074cda1e
context-lifecycle is a skill published in the GitHub repository lightninglabs/wavelength (44 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 1,585 once invoked, about $0.0003 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.