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/provision-environmentnpx skills add franzos/claude-plugins --skill provision-environmentgit 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 | $0.00077 | $0.00774 |
| Opus 5 | $0.00039 | $0.00387 |
| Sonnet 5 | $0.00015 | $0.00155 |
| Haiku 4.5 | $0.00008 | $0.00077 |
Grade A, and why
provision-environment 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provisioning a toolchain or runtime
Before you run a build, test, lint, or format command, make sure the tool is actually available, and get there without changing the user's machine. Work through these steps in order and stop at the first that succeeds.
1. Follow declared presets
If the user has declared environment facts (typically an ## Environment block in their ~/.claude/CLAUDE.md, which you receive automatically), follow them: the container runtime to use, the package manager, how toolchains are provided, whether to format in a container, and so on. These win over anything you would infer.
2. Detect what is already there
Probe, do not assume. Check without side effects:
- Binaries:
command -v <tool>(never run a tool just to see if it errors). - Container runtime: a present binary is not enough, confirm the daemon:
docker info >/dev/null 2>&1, elsepodman info >/dev/null 2>&1.podmanis a drop-in fordocker. - Language package manager: resolve from the lockfile, not from what is installed (
pnpm-lock.yaml-> pnpm,package-lock.json-> npm,yarn.lock-> yarn,bun.lockb-> bun). - Declared project environment: prefer whatever the project ships:
manifest.scm,flake.nix, a devcontainer,.tool-versions/.mise.toml,.nvmrc,rust-toolchain.toml. - OS:
uname -s(Linux/Darwin). Assume a POSIX shell; if it is something else, say so and ask.
If the tool the task needs is already on PATH, use it and move on.
3. Provision only non-invasively
If the tool is missing, you may still proceed only by means that leave the host unchanged:
- An ephemeral shell:
nix shell ...orguix shell ...(transient, nothing installed into a profile). - A throwaway container run, for example formatting Rust with no local toolchain:
docker run --rm -v "$PWD":/w -w /w rust:<toolchain-version> sh -c "rustup component add rustfmt && cargo fmt"(usepodmanif that is the available runtime).
Never modify the host to satisfy a requirement: no apt/dnf/brew/pacman/apk installs, no global rustup component add on the host, no sudo, no writing to system paths. Provisioning is allowed to be transient, never permanent.
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 · 43 lines · 77 tokens per session scan A 56a04c7cd98d
provision-environment is a skill published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 21d ago), licensed MIT. It adds 77 tokens to every session and 774 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…