agent-isolation

agent-isolation is a skill for Claude Code, Codex from vmobifystudio/app-dev-team. It costs 82 tokens per session (2,946 once invoked), scanned A, original, MIT.

Use before spawning any agent that writes files, and by every developer/fixer agent as its first and last action. Gives each agent its own git worktree, forbids blanket staging, and requires confirming a mutation actually landed. Triggers from /app-build, /app-audit, parallel-orchestrator, and any parallel agent…

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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.

agentmods
npx agentmods add skills/vmobifystudio/app-dev-team/agent-isolation
Any agent
npx skills add vmobifystudio/app-dev-team --skill agent-isolation
Clone the repo
git clone --depth 1 https://github.com/vmobifystudio/app-dev-team

Made for: Claude Code, Codex.

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 agent-isolation

README.md
[![agentmods](https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/agent-isolation.svg)](https://agentmods.dev/skills/vmobifystudio/app-dev-team/agent-isolation)
Your own site
<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/agent-isolation"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/agent-isolation.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,946 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00082 $0.02946
Opus 5 $0.00041 $0.01473
Sonnet 5 $0.00016 $0.00589
Haiku 4.5 $0.00008 $0.00295

Measured today against content hash 48f54352abc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 today.

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.

skills/agent-isolation/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent isolation

Parallel agents that share one working tree corrupt each other. Not "might" — do.

The default developer method is: write the files, then git checkout -b feat/APP-NNN and commit. Run two of those concurrently in one tree and the sequence is:

dev A writes  ui/TodoListUiState.kt          (on main, untracked)
dev B writes  data/InMemoryTodoRepository.kt (on main, untracked)
dev A runs    git checkout -b feat/APP-001   -> B's file comes along
dev A runs    git add . && git commit        -> A ships B's half-finished work
dev B runs    git checkout -b feat/APP-002   -> from A's branch, inheriting A's commit

Both branches are now wrong, and neither agent can tell. Worse, this is silent: every agent reports DONE, tests pass, and the review reads a diff that contains someone else's changes.

A read-only agent is not exempt. A verification agent sharing a working tree once left a billing file with its guest-purchase guard deleted. Only explicit-path staging kept it out of the commit. One git add -A ships a removed billing guard.

Rule 1 — one worktree per WRITING AGENT, always

Before spawning any agent that writes, the orchestrator leases its slot:

node "${CLAUDE_PLUGIN_ROOT}/scripts/worktree-slot.mjs" lease --owner ios-developer --tickets APP-001,APP-002

The agent is given that path — .agent-wt/ios-developer — as its project root and never leaves it. Its git commands are confined there. It cuts feat/APP-001-short-slug, commits, then cuts feat/APP-002-short-slug from the same base and commits: one branch per ticket, unchanged. Parallel agents cannot see each other's uncommitted state, because they do not share a tree.

The slot is keyed by the WRITER, and it used to be keyed by the ticket. That was a contradiction, not a preference. parallel-orchestrator step 2 says one agent invocation per owner, batched; step 3 says each agent's prompt names its worktree path, singular. An ios-developer owning three tickets was spawned once, given three worktrees, and told to stand in one path that did not exist. Working all three in one of them makes every branch carry its siblings' files, which code-reviewer check 9 rejects — sending tech-manager to hunt a shared-tree collision the orchestrator caused.

Read the full file on GitHub · 224 lines

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. today First seen · 224 lines · 82 tokens per session scan A 48f54352abc4

Subscribe to this mod's changes

agent-isolation is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 24d ago), licensed MIT. It adds 82 tokens to every session and 2,946 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 2026-09-03.

Related

Other skills, from other repositories

execute-task

Implement one task (or a cohesion bundle) from a signed-off spec (Ready or Active): recompute the execution freshness gate, write the verifying test first, implement to green, run the project's full CI with adaptive retry, converge via the configured reviewsequence (default /polish --nested), then open a draft PR…

inkatze/planwright · 111 tokens

builder

Detect a project's stack and recommend or apply the universal mechanical quality guards from planwright's core catalog (formatter, linters, type-checker, test runner, secret scan, commit hooks, CI gate), plus the growable breadth dimensions. Escalates stake-bearing decisions (auth, data modeling, security posture…

inkatze/planwright · 100 tokens

spec-walkthrough

Render a spec bundle (or a chosen slice) into a plain-language, didactic comprehension artifact a human reads and judges for themselves: an unaided cold read before kickoff, re-orientation mid-execution, or onboarding to a finished or abandoned spec. Standalone and strictly read-only: it renders any status, never…

inkatze/planwright · 100 tokens

drain

Run the on-demand drain pass over every spec bundle's Gate deferral entries: evaluate structured GATE(when:) conditions, surface date and free-text gates, report malformed ones, inventory each live bundle's [manual] test-spec entries, and surface the observations log's unmined state. Read-only; nothing is…

inkatze/planwright · 75 tokens

orchestrate

Advance one planwright spec by one step: pick the next ready unit critical-path-first (or a cohesion bundle), run the freshness gate, record the dispatch under the per-spec lock, and dispatch /execute-task via the backend. A stateless, disposable control tower; a reconcile sweep rebuilds from disk. Never merges, marks…

inkatze/planwright · 101 tokens

spec-kickoff

Walk a spec bundle section by section to mutual understanding, producing the signed-off kickoff brief downstream skills execute from. On sign-off: runs the Discovery-Rigor lens pass, flips Draft to Ready, records the sign-off record (anchor last), commits, pushes, opens a draft PR, then on clean completion marks the…

inkatze/planwright · 108 tokens