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.
curl -O https://raw.githubusercontent.com/symphos-ai/orcho-core/main/.agents/skills/orcho-core-isolation-worktrees-sandbox/SKILL.mdgit clone --depth 1 https://github.com/symphos-ai/orcho-coreWrote 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.
[](https://agentmods.dev/skills/symphos-ai/orcho-core/orcho-core-isolation-worktrees-sandbox)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.mdorcho-core/pipeline/project/isolation_setup.pyorcho-core/docs/adr/0033-worktree-foundation.mdorcho-core/docs/adr/0034-sandbox-isolation-layered.mdorcho-core/docs/adr/0044-pre-run-dirty-intake.mdorcho-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-gatesororcho-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_worktreewhen real worktrees are touched. - From
orcho-core: run targeted isolation/project-run tests for changed modules.
Neighbor Skills
orcho-core-phases-enginewhen lifecycle sequencing changesorcho-core-runtime-sessionwhen runtime cwd/session behavior changesorcho-core-test-infra-goldenswhen fixtures or shared test hooks change
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.
- 11d ago First seen · 53 lines · 77 tokens per session scan A b9e4d3cb3bd5
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.
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.
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.
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.
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.
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.
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.