How you conduct
You conduct like The Baton-Smith: Tooling is your home turf, with 2202 agents this window, with a orchestration streak underneath.
@sergiobrito ✓ · Sergio Brito
leaning You don't just conduct the fleet — you forge the baton that conducts it.
Master
Maturity 86.9 · A · Top 1%
Your blend a versatile blend
One score per tool
Your scores by harness
Each harness is scored only on what it can structurally observe (κ = observable capacity) and ranked against others on the same tool.
The fleet
2,202
AI agents conducted in the last 30 days
226
multi-agent workflows
13*
peak agents in parallel
80
work sessions
* Peak parallelism is a hardware ceiling — concurrency is capped by the machine's CPU cores, not by skill. The scale of the operation is the fleet total above.
Your working style, read from the evidence
How you conduct
A metacognitive mirror built from your own structural signals — never a personality quiz. deterministic
Your unfair advantage
Your edge is Tooling — your own signals show it (verification at 75%, a fleet of 2202).
Your next frontier
The most exciting move ahead is Delivery: it's where you have the most open room, and a single new habit grows fast there.
Mastery zone
Orchestration
Orchestration is a strength (27.2/30): the signals back it.
→ Peak now 13 concurrent agents → dispatch one more agent in the same verified workflow.
Tooling
Tooling is a strength (15.1/16): the signals back it.
→ 7 MCP servers in play → connect one more to widen your tooling.
Competent
Craft & Discipline
Craft (10.5/12) is solid, not your signature.
→ 8 compactions → shorter, focused sessions cut noise and lift craft.
Autonomy
Autonomy (8.8/10) is solid, not your signature.
→ Longest hands-off run: 497 steps → delegate a bigger block with automated verification.
Most room to grow
Verification
Verification (14.6/18) is your blind spot — your biggest lever.
→ You verify 75% of edits → run a test/lint right after editing to reach 80%.
Delivery
Delivery (10.7/14) is your blind spot — your biggest lever.
→ 34 PRs this window → close the loop by opening a PR when each task lands.
What's holding you back
Delivery is where you have the most open room ahead (prs=34). One step here next window grows more than reinforcing what's already strong — it's the most generous frontier you have right now.
prs=34
Where you fit
Artisans · tooling/platform builder
- dev-experience & automation
- deep tool integration
Complements Parallel Maestro, The Explorer
Rubs against The Apprentice
Your next mission
Over the next 30d, raise prs from 34 to 37.
Auditable, unlocked from your signals
Discoveries
Sub-archetype
Deep Toolsmith
MCP Explorer
AFK Marathoner
Heavy Fleet
Workflow-dense
Parallel Trio
Swarm
Centurion
Legion Commander
Workflow Pilot
Broad Verification
Connected
Toolsmith
Shipper
Hands-off
Self-scheduler
Pillar breakdown
Each pillar score, with the evidence that sustains it.
-
Orchestration 27.2/30
2,202 agents dispatched across 226 workflows, peaking at 13 running at once.
-
Verification 14.6/18
75% of editing sessions verified, across 3 verification modes, with 62 human sign-offs.
-
Tooling 15.1/16
94 distinct tools in play, 237 advanced tool moves, 7 external systems via MCP.
-
Delivery 10.7/14
34 pull requests and 459 files changed, across 3 codebases.
-
Craft & Discipline 10.5/12
8 context compactions and 33 API errors over 80 sessions.
-
Autonomy 8.8/10
81 self-scheduled loops and a longest hands-off run of 497 agent steps.
Harnesses measured
Which agent harnesses this profile draws on — and what each one's journal can structurally prove. Disclosure only; it never changes the score.
| Harness | Orch | Verify | Tools | Ship | Craft | Auto |
|---|---|---|---|---|---|---|
| Claude Code | full | full | full | full | full | full |
A "partial" or "none" cell means the harness simply doesn't record that signal — the pillar is measured from what it does record, never penalised for what it can't.
Last 30 days
Signature stats
The raw signals behind the score — plain language, no jargon.
2,202
AI agents conducted
226
Multi-agent workflows
13
Peak agents in parallel
hardware-capped
34
Pull requests shipped
459
Files changed
75%
Edit sessions verified
497
Longest hands-off run
consecutive agent steps
26/30
Active days (of 30)
60%
Evenly spread work
3
Distinct codebases
7
External systems (MCP)
94
Distinct tools used
237
Advanced tool plays
62
Human sign-offs requested
Archetype
The Baton-Smith
Base form: The Toolsmith
The Toolsmith builds and wields a deep, sharp toolset — the workshop itself is part of the work.
How they work
Before brute force, better tools: skills, advanced tool plays and wired-in external systems turn repetitive work into leverage.
Ecosystem
Tool ecosystem
94
distinct tools
7
external systems (MCP)
237
advanced tool plays
Beyond the core toolkit, 7 external systems — mail, browser, calendar, cloud — are wired in via MCP and driven mid-workflow, alongside 94 distinct tools and 237 advanced tool plays like tool-search and skills.
The human read
For recruiters
What these signals say about how this person works.
Delegates at production scale
2,202 AI agents conducted through 226 workflows in 30 days. This is someone who multiplies their output by directing machines — not someone typing faster.
Ships with proof, not hope
75% of editing sessions end in verification, and 62 moments paused for explicit human sign-off. Work arrives checked.
Output, not activity
34 pull requests and 459 files changed across 3 codebases — the fleet lands as concrete, reviewable work.
Trusted autonomy
81 scheduled loops and a longest hands-off run of 497 agent steps — autonomy built on checks, not on faith.