agentmods.dev

fr-isolation

fr-isolation is a skill for Claude Code from derio-net/super-fr. It costs 105 tokens per session (1,756 once invoked), scanned A, original, MIT.

A workflow for running development work in a separate Git worktree and development container. A Git worktree is an additional checkout of a repository, while a development container provides an isolated working environment.

In plain words
What is it for?
Use it when feature work must be isolated, when commands should run inside a container, or when the operator asks to run or clean up isolated work.
Why use it?
It keeps feature work separate from the base repository and defines how commands, credentials, and cleanup are handled. This reduces the chance that experiments change the main working copy.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event.

not rated 1repo 2d ago A scan 105 tokens original MIT

Good fit Use it when feature work must be isolated, when commands should run…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/derio-net/super-fr/fr-isolation
View source ↗ derio-net/super-fr
Install

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.

Any agent
npx skills add derio-net/super-fr --skill fr-isolation
Clone the repo
git clone --depth 1 https://github.com/derio-net/super-fr

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fr-isolation

README.md
[![agentmods](https://agentmods.dev/badge/skills/derio-net/super-fr/fr-isolation.svg)](https://agentmods.dev/skills/derio-net/super-fr/fr-isolation)
Your own site
<a href="https://agentmods.dev/skills/derio-net/super-fr/fr-isolation"><img src="https://agentmods.dev/badge/skills/derio-net/super-fr/fr-isolation.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,756 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00105 $0.01756
Opus 5 $0.00053 $0.00878
Sonnet 5 $0.00021 $0.00351
Haiku 4.5 $0.00011 $0.00176

Measured 6d ago against content hash dd1fa6cbd7b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fr-isolation 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 6d 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.

.hermes/skills/fr/fr-isolation/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fr-isolation

A workspace contract, not just a worktree: code lives in a git worktree OUTSIDE the repo (~/.cache/fr/worktrees/<repo>/<branch>), commands run inside the profile's devcontainer, and the base repo is never touched while the run is live. The surface is plain shell — any agent or a human drives it identically.

Announce at start: "I'm using fr-isolation to run this work isolated."

Hard requirements

  • Must run inside a git repo.
  • devcontainer mode (default) needs ≥1 devcontainer profile (.devcontainer/<profile>/devcontainer.json). Missing → fr isolation exits 2 pointing at fr-init. NEVER proceed unisolated; offer the fr-init interview (autonomous run: pause, interview, resume).

Modes (FR_ISOLATION_TARGET) — host env / docker-less

Same worktree + exec-bridge + cleanup contract in all three; only the environment half differs (the profile requirement is devcontainer-mode's).

  • host-worktree (=worktree): fr worktree, the host process env as-is — NO profile, no secrets provisioning (pods carry their own creds). A host-level declaration (pod/image env), never a per-call flag.
  • external (valid preparer-written .fr-isolation marker, mode:external): fr adopts the container's checkout — up --branch just ensures the branch in place; restart/stats refuse, gc reports (the container's owner runs both).

Unknown FR_ISOLATION_TARGET fails closed naming devcontainer|worktree.

Lifecycle

fr isolation up --branch <feature-branch> [--profile <name>]   # worktree + container
fr isolation exec --branch <feature-branch> -- CMD ...          # every build/test/run
fr isolation status [--branch ...] [--format json] [--stats] [--push-check]  # state; --stats: docker resource use; --push-check: remotes + host-push guidance
fr isolation restart [--branch ...] [--force]                   # bounce a wedged container, worktree kept
fr isolation down --branch <feature-branch> [--force]           # immediate teardown (verifies + reaps image)
fr isolation down --all [--force]                               # tear down ALL + clear pipeline sentinel(s)
fr isolation gc [--repo <path>] [--dry-run] [--format json]     # reconcile fr-owned workspaces (works in ALL three modes)

Read the full file on GitHub · 121 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago First seen · 121 lines · 105 tokens per session scan A dd1fa6cbd7b0

Subscribe to this mod's changes

fr-isolation is a skill published in the GitHub repository derio-net/super-fr (1 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 1,756 once invoked, about $0.0005 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.

Claude CodeContainersDevOps and cloudGit and workflowagent-skillsai-agentsautomationclaude-code-plugindevcontainers
Related

Other skills, from other repositories

release

CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.

oliver-kriska/claude-elixir-phoenix · 60 tokens

catchup

Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.

oliver-kriska/claude-elixir-phoenix · 48 tokens

pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 59 tokens

phx-pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 61 tokens

watch-pr

Watch an Elixir/Phoenix PR with an Amp Orb keep-alive lease until required non-deployment CI is green and review threads are resolved. Use after opening or updating a PR.

oliver-kriska/claude-elixir-phoenix · 41 tokens

deploy

Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays. Use when configuring Fly.io, Docker, CI/CD, health checks, or production migrations.

oliver-kriska/claude-elixir-phoenix · 46 tokens