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/securitynpx skills add Tiltely/lens --skill securitygit 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 | $0.00068 | $0.01123 |
| Opus 5 | $0.00034 | $0.00562 |
| Sonnet 5 | $0.00014 | $0.00225 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
security 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 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.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Lens of Security
Read first: ${CLAUDE_PLUGIN_ROOT}/core/protocol.md and ${CLAUDE_PLUGIN_ROOT}/core/dossier.md.
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.
- Audit mode: below.
Before asking anything
- Read the dossier if valid — resolve it per dossier.md (the branch-scoped path). For every battery question already answered there, SKIP it and print the skip line.
- Ensure
stack:is known (core/stack-detection.md) — it selects 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)
- What is at stake here — what data or capability would an attacker want from this feature? (money, PII, account takeover, reputation)
- Who are the actors? (anonymous users, authenticated users, admins, third-party services, internal jobs)
Tier 2 — stack-conditional
If nextjs-web (any flavor):
3. Where does the session/token live — httpOnly cookie, memory, or localStorage?
Why there? (localStorage → follow up: XSS steals it; what mitigates that?)
4. How does a session end — expiry, refresh rotation, explicit logout? What happens
to in-flight requests when it does?
5. If cookies: what is the CSRF story? (SameSite value, CSRF tokens, or "we accept
the risk because…")
If nestjs-api:
6. Which layer decides AUTHORIZATION (not authentication)? Guard, service, query
filter? Can a controller be added tomorrow that forgets it?
7. Are inbound webhooks signature-verified before any side effect? Replay protection?
8. Where do secrets live at runtime, and what would leak them? (env injection at
deploy per Tiltely practice — confirm nothing persists in repo or droplet .env)
If expo-mobile:
9. Are tokens in SecureStore/Keychain (not AsyncStorage)? What is the story when the
device is lost?
10. Do deep links / universal links accept parameters that reach privileged screens?
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 · 106 lines · 68 tokens per session scan A b23b04802b62
security is a skill published in the GitHub repository Tiltely/lens (5 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 1,123 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 2026-08-31.
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…