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/tiltely/lens/observabilitynpx skills add Tiltely/lens --skill observabilitygit clone --depth 1 https://github.com/Tiltely/lensWhat 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 | $0.00080 | $0.01474 |
| Opus 5 | $0.00040 | $0.00737 |
| Sonnet 5 | $0.00016 | $0.00295 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
observability 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Lens of Observability
Read first: ${CLAUDE_PLUGIN_ROOT}/core/protocol.md and ${CLAUDE_PLUGIN_ROOT}/core/dossier.md. Dossier rules: read it, skip answered questions WITH skip lines, append your outputs.
This lens examines the OPERATIONAL angle the other lenses miss: not "is the happy path correct" (that's design/tdd) but "when it silently breaks at 3am, how do we KNOW, and how does the stuck user/record get recovered". Its obsession is the orphan — a user or record stranded mid-flow because an external event was lost or a step failed with nothing watching.
Mode selection
- Explicit argument wins ("audit" / "design").
- Otherwise infer: planning new work → design; reviewing existing code → audit. Confirm your inference in one line before starting.
Before asking anything
- Read the dossier if valid — resolve it per dossier.md (the branch-scoped path). Skip answered questions WITH skip lines.
- Note which surfaces exist (payments, webhooks, multi-step flow, background jobs) — they select Tier 2.
Question battery — design mode
Ask one at a time; follow answers per protocol.md. Append answers to the dossier.
Tier 1 — framing (always)
- Name the worst SILENT failure here: a user or record stuck mid-flow that NOTHING surfaces (paid-but-no-access, charged-twice, half-migrated, webhook-lost, stuck-PROCESSING). If you cannot name one, say so — maybe this flow does not need the lens.
- When that breaks at 3am, how do you find out, and from what? An alert, a user complaint, a dashboard, or nothing until someone notices? Who is on the hook?
Tier 2 — surface-conditional
If external events / webhooks (Stripe, SendGrid, queues, partner callbacks): 3. What happens when an inbound event is LOST, or arrives LATE / out-of-order? Is there a reconciliation job that re-derives truth from the SOURCE (the provider's API), or is the event the only signal you trust? 4. Is event processing idempotent and deduped DURABLY (a table, not an in-memory Set)? Can a redelivery double-apply an effect (double charge, double grant)?
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 · 120 lines · 80 tokens per session scan A b7d5d246ccbe
observability is a skill published in the GitHub repository Tiltely/lens (5 stars, last pushed 24d ago), licensed MIT. It adds 80 tokens to every session and 1,474 once invoked, about $0.0004 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…