orcho-core: Skill for Claude Code

.agents/skills/orcho-core-isolation-worktrees-sandbox/SKILL.md

orcho-core-isolation-worktrees-sandbox is a skill for Claude Code, Codex from symphos-ai/orcho-core. It costs 77 tokens per session (493 once invoked), scanned A, original, Apache-2.0.

A set of instructions for changing Orcho Core's workspace isolation and sandbox safety systems. A worktree is a separate Git working directory, and a sandbox limits what a run can access or do.

In plain words
What is it for?
Use it when editing worktree setup, runspace paths, dirty-change intake, sandbox rules, dependency checkouts, or related Git tests.
Why use it?
It helps protect project files and keep runs, dependencies, dirty changes, and generated workspaces separated safely.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is symphos-ai/orcho-core's own configuration. It tells Claude Code and Codex how to work on orcho-core itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orcho-core configures →

Reuse

Borrowing it

Nothing to install: this file belongs to symphos-ai/orcho-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/symphos-ai/orcho-core/main/.agents/skills/orcho-core-isolation-worktrees-sandbox/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/symphos-ai/orcho-core

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 orcho-core-isolation-worktrees-sandbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-core-isolation-worktrees-sandbox/github.svg)](https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-core-isolation-worktrees-sandbox)
Your own site
<a href="https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-core-isolation-worktrees-sandbox"><img src="https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-core-isolation-worktrees-sandbox/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 orcho-core-isolation-worktrees-sandbox

Your own site · 80×15
<a href="https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-core-isolation-worktrees-sandbox"><img src="https://agentmods.dev/badge/skills/symphos-ai/orcho-core/orcho-core-isolation-worktrees-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 493 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 $0.00077 $0.00493
Opus 5 $0.00039 $0.00246
Sonnet 5 $0.00015 $0.00099
Haiku 4.5 $0.00008 $0.00049

Measured 11d ago against content hash b9e4d3cb3bd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

orcho-core-isolation-worktrees-sandbox 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 11d 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.

.agents/skills/orcho-core-isolation-worktrees-sandbox/SKILL.md · 53 lines

What it actually says

Orcho Core Isolation Worktrees Sandbox

Own the safety boundary around checkouts, worktrees, dirty state, runspace, and sandbox policy.

First Reads

  • orcho-core/AGENTS.md
  • orcho-core/pipeline/project/isolation_setup.py
  • orcho-core/docs/adr/0033-worktree-foundation.md
  • orcho-core/docs/adr/0034-sandbox-isolation-layered.md
  • orcho-core/docs/adr/0044-pre-run-dirty-intake.md
  • orcho-core/docs/architecture/sandbox.md
  • changed worktree/sandbox modules

Owns

  • worktree selection/bootstrap and runspace paths
  • pre-run dirty intake
  • sandbox policy and launch-layer process hygiene
  • dependency checkout subjects for verification
  • generated worktree handling rules inside core

Does Not Own

  • runtime adapter sessions -> orcho-core-runtime-session
  • phase lifecycle -> orcho-core-phases-engine
  • verification command semantics -> orcho-core-quality-gates or orcho-core-test-infra-goldens

Invariants

  • Do not edit unrelated generated worktrees.
  • Tests involving git worktrees, subprocesses, shared env, or ports are serial unless proven safe.
  • Keep run worktree subject distinct from canonical project/dependency subjects.
  • Never use destructive git commands unless explicitly requested.

Verification

  • From orcho-core: python -m pytest -q -m worktree
  • From orcho-core: python -m pytest -q -m git_worktree when real worktrees are touched.
  • From orcho-core: run targeted isolation/project-run tests for changed modules.

Neighbor Skills

  • orcho-core-phases-engine when lifecycle sequencing changes
  • orcho-core-runtime-session when runtime cwd/session behavior changes
  • orcho-core-test-infra-goldens when fixtures or shared test hooks change
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. 11d ago First seen · 53 lines · 77 tokens per session scan A b9e4d3cb3bd5

Subscribe to this mod's changes

orcho-core-isolation-worktrees-sandbox is a skill published in the GitHub repository symphos-ai/orcho-core (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 493 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.

Related

Other skills, from other repositories

agentplane-task-closure-recovery

Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.

basilisk-labs/agentplane · 46 tokens

collaboration

Guide for collaborating on GitHub projects. This skill should be used when contributing to projects, creating PRs, reviewing code, or managing issues on GitHub.

aAAaqwq/AGI-Super-Team · 35 tokens

pr-feedback

Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.

jjanczur/tyran · 57 tokens

dos-verify-done-claims

Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.

anthony-chaudhary/dos-kernel · 61 tokens

review-deep

Drive the deep-review phase of an automated PR review. Consumes the walkthrough, runs the deterministic deep-review workflow (parallel lenses → adversarial validation → code-enforced threshold/caps), drafts the surviving findings, and completes the review run.

ShreyPaharia/octomux · 52 tokens

review-orchestrator

Drive an automated PR review. Produces a structured walkthrough plus inline draft comments via the octomux review CLI. NEVER posts to GitHub directly — publishing is human-gated.

ShreyPaharia/octomux · 41 tokens