The Agent Roster Playbook — 11 steps from the Grok Bot team's workflow

Condensed, credited reference of an article on how SpaceXAI and Cursor teams run narrow Grok Bot rosters: editable profiles, three-layer memory, watcher lanes, skill chaining, and bot-to-bot handoffs.

View source ↗
SafeScan verdict · score 81/100
Coverage
full
Checks run
Rule-based pattern scan
Files checked
12
Findings
0
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
81/100

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 verdict1/1Safe
Code coverage1/1full
Rule findings1/10 matched
No executable scripts1/10 script file(s) of 12
Pinned source1/1commit/SHA-256 recorded
Named author0/1unknown
Recently seen1/1last seen 2026-10-30
Install path0.5/1source URL only

Scan details

Findings
No rule matched.
Content SHA-256
2be3aa5cdac9a27a…
Commit
3c7dbe5aec
Files
README.md
docs/01-the-roster.md
docs/02-the-four-limits.md
docs/03-agent-profile-file.md
docs/04-show-the-tape.md
docs/05-chain-skills.md
+6

About

Author
DevvGwardo ↗
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