agentmods.dev

fr-isolation

fr-isolation is a skill for Claude Code from derio-net/super-fr. It costs 97 tokens per session (2,835 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. Also seen: reads .claude/ paths; mentions Claude Code; built for hermes-agent.

not rated 2repo changed 16d ago A scan 97 tokens original MIT

Good fit 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.

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/github.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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fr-isolation

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,835 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 $0.00097 $0.02835
Opus 5.5 $0.00039 $0.01134
Sonnet 5.5 $0.00019 $0.00567
Haiku 4.5 $0.00010 $0.00283

Measured 16d ago against content hash dedf4b3335a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 16d 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: a git worktree OUTSIDE the repo (~/.cache/fr/worktrees/<main-checkout>/<branch>), commands in the profile's devcontainer, base repo untouched while the run is live. Plain shell, any agent or human.

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

Hard requirements

  • Inside a git repo. devcontainer mode (default) needs ≥1 profile (.devcontainer/<profile>/devcontainer.json); missing → exit 2 pointing at fr-init. NEVER proceed unisolated; offer the fr-init interview (pause, resume).
  • host-worktree (FR_ISOLATION_TARGET=worktree, docker-less; the default in a Claude Code cloud session): host env as-is, NO profile/secrets; restart/stats refuse, stop/rebuild no-op.
  • external mode (valid preparer-written .fr-isolation marker, mode:external): fr adopts the container's checkout — up --branch ensures the branch in place; restart/stop/rebuild/stats refuse, gc reports (the container's owner runs them).
  • Any other FR_ISOLATION_TARGET value fails closed (devcontainer|worktree). It selects the mode at up only: every later command follows the workspace's recorded mode, so agents, hooks and fresh shells need no env; only up, gc's sweep and a reaped verify-merge read it.

Lifecycle

fr isolation up --branch <b> [--profile <name>] [--session <id>] [--print-path]  # worktree + container; --print-path: last stdout line = path
fr isolation exec --branch <b> -- CMD ...                                         # every build/test/run; resumes a stopped container
fr isolation status [--branch ...] [--session <id>] [--format json] [--stats] [--push-check]  # state + bound sessions
fr isolation attach|detach --session <id> [--repo <path>] [--branch ...]         # bind/unbind a harness session
fr isolation restart [--branch ...] [--force]                                     # bounce a wedged container, worktree kept
fr isolation stop [--branch ...]                                                  # free a container's resources; everything else kept
fr isolation rebuild [--branch ...] [--no-cache]                                  # recreate the container from the (changed) profile
fr isolation down --branch <b> | --worktree <path> | --all [--dry-run] [--yes] [--force] [--no-preserve]  # teardown; --all lists blast radius first
fr isolation gc [--repo <path>] [--dry-run] [--format json]                       # reconcile fr-owned workspaces, 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. 16d ago Changed dedf4b3335a9
  2. 1mo ago Changed 133914d9daec
  3. 1mo ago Changed 34afd0a957da
  4. 1mo ago Changed 76c6e018862b
  5. 1mo ago Changed a4cc65b89fd2
  6. 1mo ago Changed ec1f19f608e0
  7. 1mo ago Changed · -8 tokens per session 44d557c19d59
  8. 1mo 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 (2 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 2,835 once invoked, about $0.0004 per session on Opus 5.5. 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

devops-zeroclaw-coordination-rules

ZEROCLAW COORDINATION RULES — extracted from roles.json deepPrompt for devops.

iampantherr/SecureContext · 29 tokens

dockerized-service-release-deployment-workflow

Create a Dockerized-service release contract with clean GitHub Actions builds, main-anchored tags, immutable digest manifests, published-release deployments, production approval, health checks, and exact-digest rollback.

gaelic-ghost/socket · 49 tokens

update-pr

Update an existing pull request with new changes. Use when the user wants to update a PR, push follow-up changes to a PR, refresh a PR description, or sync a PR with latest commits. Triggers on: update pr, update-pr, update the pr, push to pr, refresh pr, sync pr, update pull request.

ReflexioAI/claude-smart · 71 tokens

update

Safe cc10x upgrade through the Claude Code plugin CLI. Lists every installed scope, refreshes the marketplace, updates each scope, and optionally carries local patches over to the new install. Use this skill when: updating cc10x, upgrading, pulling latest cc10x, syncing plugin, refreshing cache, or checking for new…

romiluz13/cc10x · 108 tokens

smart-rebase

Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — no skill executes…

sd0xdev/sd0x-harness · 133 tokens

resolving-merge-conflicts

Use when a git merge or rebase reports conflicts and the operation is in progress.

romiluz13/cc10x · 25 tokens