How you conduct
You conduct like The Precision Luthier: Tooling is your home turf, with 330 agents this window, with a verification streak underneath.
@yuki-codes ✓ · Yuki Tanaka
A sharpened tool, verified, that lets nothing slip.
Your 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
330
AI agents conducted in the last 30 days
35
multi-agent workflows
1*
peak agents in parallel
20
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 30%, a fleet of 330).
Your next frontier
The most exciting move ahead is Autonomy: it's where you have the most open room, and a single new habit grows fast there.
Mastery zone
Orchestration
Orchestration is a strength (19.7/30): the signals back it.
→ Peak now 1 concurrent agents → dispatch one more agent in the same verified workflow.
Tooling
Tooling is a strength (12.2/16): the signals back it.
→ 6 MCP servers in play → connect one more to widen your tooling.
Competent
Verification
Verification (11.6/18) is solid, not your signature.
→ You verify 30% of edits → run a test/lint right after editing to reach 80%.
Craft & Discipline
Craft (7.7/12) is solid, not your signature.
→ 26 compactions → shorter, focused sessions cut noise and lift craft.
Most room to grow
Delivery
Delivery (6.7/14) is your blind spot — your biggest lever.
→ 6 PRs this window → close the loop by opening a PR when each task lands.
Autonomy
Autonomy (2.7/10) is your blind spot — your biggest lever.
→ Longest hands-off run: 10 steps → delegate a bigger block with automated verification.
What's holding you back
Autonomy is where you have the most open room ahead (afk_max_run=10). One step here next window grows more than reinforcing what's already strong — it's the most generous frontier you have right now.
afk_max_run=10
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 afk_max_run from 10 to 40 and unlock the Autopilot archetype.
The Autopilot
Auditable, unlocked from your signals
Discoveries
Sub-archetype
Deep Toolsmith
MCP Explorer
Workflow-dense
Tool Scout
Broad Verifier
Centurion
Workflow Pilot
Broad Verification
Connected
Toolsmith
Shipper
Pillar breakdown
Each pillar score, with the evidence that sustains it.
-
Orchestration 19.7/30
330 agents dispatched across 35 workflows, peaking at 1 running at once.
-
Verification 11.6/18
30% of editing sessions verified, across 4 verification modes, with 9 human sign-offs.
-
Tooling 12.2/16
21 distinct tools in play, 166 advanced tool moves, 6 external systems via MCP.
-
Delivery 6.7/14
6 pull requests and 67 files changed, across 4 codebases.
-
Craft & Discipline 7.7/12
26 context compactions and 17 API errors over 20 sessions.
-
Autonomy 2.7/10
2 self-scheduled loops and a longest hands-off run of 10 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.
330
AI agents conducted
35
Multi-agent workflows
1
Peak agents in parallel
hardware-capped
6
Pull requests shipped
67
Files changed
30%
Edit sessions verified
10
Longest hands-off run
consecutive agent steps
14/30
Active days (of 30)
79%
Evenly spread work
4
Distinct codebases
6
External systems (MCP)
21
Distinct tools used
166
Advanced tool plays
9
Human sign-offs requested
Archetype
The Precision Luthier
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
21
distinct tools
6
external systems (MCP)
166
advanced tool plays
Beyond the core toolkit, 6 external systems — mail, browser, calendar, cloud — are wired in via MCP and driven mid-workflow, alongside 21 distinct tools and 166 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
330 AI agents conducted through 35 workflows in 30 days. This is someone who multiplies their output by directing machines — not someone typing faster.
Ships with proof, not hope
30% of editing sessions end in verification, and 9 moments paused for explicit human sign-off. Work arrives checked.
Output, not activity
6 pull requests and 67 files changed across 4 codebases — the fleet lands as concrete, reviewable work.
Trusted autonomy
2 scheduled loops and a longest hands-off run of 10 agent steps — autonomy built on checks, not on faith.