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/newnpx skills add Tiltely/lens --skill newgit 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 | $0.00044 | $0.01067 |
| Opus 5 | $0.00022 | $0.00534 |
| Sonnet 5 | $0.00009 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
new 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Lens Scaffolder
Every lens — bundled or one you create — is used the same way: through
/lens:socratic, which discovers and applies it. Lenses you create are NOT separate
slash commands; only the bundled set has /lens:<name> shortcuts (a Claude Code
namespace limit, not a choice). So a new lens just needs a HOME + a registry row that
socratic reads. Draft the battery socratically first (step 3), then write it to the
chosen scope — no commit, no plugin rebuild, no reload; socratic reads it fresh.
Offer the SCOPE — but only the options that apply to the current context (never ask about "maintaining the plugin"; that option appears on its own, below, only when you detect you're inside the lens plugin repo):
- Project — applies only in THIS repo (when cwd is in a git repo). Write to
<repo>/.lens/lenses/<name>/SKILL.mdfrom the template (no surviving placeholders), append the row to<repo>/.lens/registry.md(create if absent), and git-exclude.lens/viagit rev-parse --git-path info/exclude(handles worktrees/submodules; on failure PROPOSE a.gitignoreentry — never silently edit it). To SHARE it with the team, commit its SKILL.md to<repo>/.claude/skills/lens-<name>/(Claude Code loads that one natively as a slash command). - Global — applies everywhere on this machine. Write to
<foundry>/lenses/<name>/SKILL.mdand append the row to<foundry>/registry.md(foundry from the config:$LENS_CONFIG→~/.claude/lens.json→~/lens/lens.json). Lives in the foundry, outside the plugin — auto-updates never touch it. A global lens that earns its keep can be PR'd into the bundled set. - No foundry config and not in a repo: write the drafted lens to
./lens-proposal-<name>.mdwith a note on how to add it later, and point at /lens:setup.
Maintainer path — auto-detected, never asked. Offer "into the bundled set" ONLY
when the current git repo IS the lens plugin itself — detect it: the repo root
(git rev-parse --show-toplevel) contains .claude-plugin/plugin.json whose name
is lens. That is the only signal; there is no pluginRepo config and no setup
question. If detected, the steps below apply (the plugin repo is the cwd's repo root).
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 · 65 lines · 44 tokens per session scan A 02e781629d97
new is a skill published in the GitHub repository Tiltely/lens (5 stars, last pushed 23d ago), licensed MIT. It adds 44 tokens to every session and 1,067 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.