Sandbox Routing SKILL.md skillA

Sandbox Routing from wrg32786/aigent-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wrg32786/aigent-os/Sandbox Routing@git:20260707.2a2e857

Pins git:20260707.2a2e857 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wrg32786/aigent-os
Path
skills/sandbox-routing/SKILL.md
Versions recorded
1
Latest version
git:20260707.2a2e857, committed Jul 7, 2026
Size
4,340 bytes
Repository stars
24
License
MIT

SELF-CORRECT tool choice. About to Read a long file just to extract one piece of info? Use a sandbox tool that returns only the summary. About to run a long shell command? Same. Sandbox keeps raw output OUT of context — only summaries land. Triggers when about to flood context with large output.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Sandbox Routing

> [!danger] HARD RULE — fires before any large Read or Bash that isn't for editing
> If you're about to Read a long file to *analyze* (not to Edit), or run a Bash command with >20 line output, **route through sandbox tools instead**. Raw output stays out of context; only the summary you print enters context.

This skill assumes your Claude Code install includes context-mode (or equivalent) sandbox tools — `ctx_execute`, `ctx_execute_file`, `ctx_batch_execute`. If those aren't available, the principle still applies: use `head_limit` on Grep, narrow Read to specific line ranges, and avoid `cat large.log`.

## The decision tree

```
Am I about to Read or run Bash?
   ├── Editing a file? (need full content for Edit tool)
   │     → Read is correct, proceed
   │
   ├── Running git status / git log -n short / mkdir / mv / rm / short command?
   │     → Bash is correct, proceed
   │
   ├── Reading a file just to extract a piece of info / find a line?
   │     → STOP. Use ctx_execute_file with grep/awk code that prints just the answer.
   │
   ├── Running a shell command with >20 line output?
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wrg32786/aigent-os/Sandbox Routing@sha256:893474882aacefff

The line at the top of this page pins the label git:20260707.2a2e857, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5ctjclk4cxm2lhbu.svg)](https://markdownregistry.com/a/art_5ctjclk4cxm2lhbu)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 7, 2026.

versioncommittedcommitsizeaudit
git:20260707.2a2e857 latest2026-07-07 2a2e857 4,340 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4340 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

wrg32786/aigent-os · 24 stars · license MIT · pushed 2026-10-19 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_5ctjclk4cxm2lhbu
GET https://markdownregistry.com/api/v1/resolve?ref=wrg32786/aigent-os/Sandbox Routing
GET https://markdownregistry.com/api/v1/blob/893474882aacefff8002e50ca422579a2eba6c55931ef803e486916a69eede33

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wrg32786/aigent-os

CLAUDE.md CLAUDE.md file
wrg32786/aigent-os · CLAUDE.md
git:20260730.ebbe603 · audit A · 24 stars
agent-fitness SKILL.md skill
wrg32786/aigent-os · skills/agent-fitness/SKILL.md · Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger…
git:20260707.2a2e857 · audit A · 24 stars
body-check SKILL.md skill
wrg32786/aigent-os · skills/body-check/SKILL.md · Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures +…
git:20260707.2a2e857 · audit A · 24 stars
brief SKILL.md skill
wrg32786/aigent-os · skills/brief/SKILL.md · Generate a structured delegation brief for any task
git:20260707.2a2e857 · audit A · 24 stars
Caddy Audit SKILL.md skill
wrg32786/aigent-os · skills/caddy-audit/SKILL.md · Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed…
git:20260707.2a2e857 · audit A · 24 stars
caddy-enroll SKILL.md skill
wrg32786/aigent-os · skills/caddy-enroll/SKILL.md · Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created…
git:20260707.2a2e857 · audit A · 24 stars
Caddy Explain SKILL.md skill
wrg32786/aigent-os · skills/caddy-explain/SKILL.md · When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which…
git:20260707.2a2e857 · audit A · 24 stars
caddy-mute SKILL.md skill
wrg32786/aigent-os · skills/caddy-mute/SKILL.md · Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
git:20260719.404ad2a · audit A · 24 stars
capsule-compact SKILL.md skill
wrg32786/aigent-os · skills/capsule-compact/SKILL.md · Compact a long capsule chain. Walks parent_capsule_id backward from a head capsule; if chain >= 5, summarizes oldest 3…
git:20260707.2a2e857 · audit A · 24 stars
close SKILL.md skill
wrg32786/aigent-os · skills/close/SKILL.md · Commit the session to durable vault memory and prepare a clean resume point
git:20260726.7992efa · audit A · 24 stars
codex-adapter SKILL.md skill
wrg32786/aigent-os · skills/codex-adapter/SKILL.md · Route ONE bounded, mechanical task to the Codex CLI as a non-Claude executor, under the same review-before-merge gate…
git:20260724.c1e7aa7 · audit A · 24 stars
cognitive-update SKILL.md skill
wrg32786/aigent-os · skills/cognitive-update/SKILL.md · Conservative close-parity updates to GOAL_STACK, BELIEF_STATE, SELF_MODEL, and PROCEDURES. Writes only explicit or…
git:20260726.7992efa · audit A · 24 stars

Every file in wrg32786/aigent-os

Browse by kind, by grade A, or by owner.