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/setupnpx skills add Tiltely/lens --skill setupgit 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 | $0.00777 |
| Opus 5 | $0.00040 | $0.00388 |
| Sonnet 5 | $0.00016 | $0.00155 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade B, and why
setup scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
from other projects' sessions. Do NOT edit `~/.claude/settings.json` yourself — How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lens Setup (Claude Code)
The memory loop — a SessionEnd hook that queues lens sessions, /lens:retro to mine
them, /lens:new to grow your collection — is a Claude Code feature. Setup
creates your foundry and wires it up. Without setup, all bundled lenses and
/lens:socratic still work; setup only adds the loop.
On Claude Cowork: not supported — stop here
If you detect Cowork, do NOT set up a foundry. The memory loop does not run on Cowork:
its sandbox spawns the CLI with --setting-sources user, so plugin-provided hooks (the
SessionEnd queue) never fire, and the VM home is ephemeral. Tell the user plainly: on
Cowork, just use the lenses and /lens:socratic directly — they work fully. Run
/lens:setup on Claude Code to enable the loop there. Then stop — no foundry, no
config, no folder grant.
On Claude Code: set up the loop
The foundry holds PERSONAL session data (session IDs, project/transcript paths, mined observations) — never commit it to git. Use a private, persistent, non-tracked folder.
-
Choose the foundry location — default
~/.claude/lens-foundry/; any non-git folder is fine, but NEVER inside a git working tree. Create it with emptypending-retros.jsonlandprocessed-retros.jsonl, anobservations.mdwith a one-line header ("Cross-project learnings mined by /lens:retro; append-only"), aregistry.md(your lenses — same columns as${CLAUDE_PLUGIN_ROOT}/core/registry.md, starting empty), and an emptylenses/dir (where/lens:newwrites your global lenses;/lens:socraticreads them inline). -
Write the config at
~/.claude/lens.json(show the user first):{ "foundry": "<foundry path>" } -
Hand the user the cross-cwd permission rule so retro/hook writes never prompt from other projects' sessions. Do NOT edit
~/.claude/settings.jsonyourself — permission-widening by an agent is blocked by the auto-mode classifier by design. Print a paste-readynode -eone-liner the USER runs, merging into their settings and preserving everything else:
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.
- yesterday First seen · 55 lines · 80 tokens per session scan B b08eec255e11
setup is a skill published in the GitHub repository Tiltely/lens (5 stars, last pushed 23d ago), licensed MIT. It adds 80 tokens to every session and 777 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…