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/franzos/claude-plugins/setupnpx skills add franzos/claude-plugins --skill setupgit clone --depth 1 https://github.com/franzos/claude-pluginsWhat 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 | $0.00118 | $0.01406 |
| Opus 5 | $0.00059 | $0.00703 |
| Sonnet 5 | $0.00024 | $0.00281 |
| Haiku 4.5 | $0.00012 | $0.00141 |
Grade A, and why
setup 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting up Forseti
Forseti is a single Rust binary that fronts Ory Kratos (identity) and Ory Hydra (OAuth2/OIDC) and turns them into a drop-in OIDC provider plus an admin console. A full deployment is: Forseti + Kratos + Hydra + Postgres, and a mail provider. Do not hardcode the schema from memory: the operator guide and the shipped example configs are the source of truth. Read them from the deployment you are working on.
Work through these in order. Confirm the choice at each fork with the user rather than guessing.
1. Locate the deployment and pick a shape
Find what you are working with: a repo checkout (docs/operator-guide.md, config.example.toml, infra/), a release tarball, or a container image (ghcr.io/franzos/forseti). Then pick the runtime shape and confirm it:
- Docker playground stack (fastest):
infra/docker-compose.ymlbrings up Postgres, Kratos (+migrate), Hydra (+migrate), and a mail sink; Forseti itself runs on the host and Kratos reaches it viahost.docker.internal:8081. Driven by theMakefile(make stack-up,stack-up-saml). - Native: prebuilt tarball (
cp config.example.toml config.toml, edit,./forseti; runtime deplibpq5), a Cargo build (make build/make run), or a Guix build againstmanifest.scm. Kratos, Hydra, and Postgres are provided separately.
Read the prerequisites and topology sections of docs/operator-guide.md before proceeding, and docs/operator-guide-proxy.md if this sits behind a reverse proxy.
2. Provision the toolchain (native builds only)
If building from source, get a toolchain without touching the host: invoke the provision-environment skill (prefer the project manifest.scm via guix shell). Skip for tarball or container installs.
3. Bring up the dependencies
Stand up Postgres, Kratos, and Hydra. With the playground: make stack-up (init DB + migrations are wired in). Otherwise deploy Kratos and Hydra yourself and point them at Postgres. Generate their config securely rather than copying dev files verbatim:
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 · 64 lines · 0 tokens per session scan A 2be2710a392e
setup is a skill published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 20d ago), licensed MIT. It adds 118 tokens to every session and 1,406 once invoked, about $0.0006 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…