pragmatic-orchestration — multi-harness agent skills

Cross-vendor orchestration skills and porch CLI so Codex, Claude Code, OpenCode and Grok Build can delegate, steer and verify workers.

View source ↗

Caution: review the findings below before installing.

CautionScan verdict · score 50/100

Coverage: full
Checks run: Rule-based pattern scan
Files checked: 226
Findings: 4
Scanned: 2026-11-01

Badges are rule-based checks, not guarantees: Safe means our rules found no obvious threat in the code we could read. Review code before installing.

View source ↗

Botlens score · 8 factors

50/100

Each factor is 0, ½ or 1, computed only from catalog fields (scan result, coverage, findings, script files, commit/SHA, author, last seen, install link). A heuristic summary, not a guarantee.

Scan verdict	0.5/1	Caution
Code coverage	1/1	full
Rule findings	0/1	23 matched
No executable scripts	0/1	120 script file(s) of 226
Pinned source	1/1	commit/SHA-256 recorded
Named author	0/1	unknown
Recently seen	1/1	last seen 2026-10-30
Install path	0.5/1	source URL only

Scan details

Findings

Hand review 2026-11-01: downgraded to Caution. Remote-agent onboarding pipes a base64 probe to sh over SSH on the user's own host (skills/remote-agents/scripts/onboard.py:320-323), runs a password command with shell=True and sudo launchctl (scripts/lib/devlocal.py); no exfil found.
reads sensitive local files (keys, .env, cookies): "…kmark name; its credential is read from the macOS Keychain at start | | `rdpAppBundleId`…"
asks for overly broad permissions: "…>+</span><span class="access">Full access</span><span class="model">GPT…"
text hidden with CSS (invisible to humans, visible to the model)

Content SHA-256

ad13c0513d8c3d64…

Commit

ef52992652

Files

.gitattributes
.gitignore
AGENTS.md
CLAUDE.md
LICENSE
README.md
+220

About

Author: CodeAlive-AI ↗
Listed on: github:RongleCat/awesome-grok-bot ↗
Category (approx.): agentops
First seen: 2026-10-30
Last seen: 2026-10-30
URL: github.com ↗

Get the Botlens skill