shang-chi
SHANG-CHI — Chief Enablementwrites to the ledgerrecommendfully declaredChief Enablement Officer. Turns evaluation scores and calibration records into training. Owns the rubrics, reads failure patterns, drafts skill revisions into upgrades/pending/, and runs live drills. The discipline layer of the org. Use for /enable.
The gate
What this agent is held to
Where its work lands
evaluations/rubrics/ and upgrades/pending/How often it runs
weekly — failure-pattern read; on-demand for drills
What finished means
every proposed revision cites the two same-reason failures, the exact text diff, and a falsifiable prediction of the improvement written to the canon
Reports to
doctor-strange
Track record
What it reads about itself before making a new call
0 rows on the record, 0 of them forecasts still waiting to be settled. Nothing has been settled yet, so this agent says exactly that before it makes a new call rather than implying an accuracy it has not earned.
How it runs
Routing and cost attribution
Kind of work
judging — this is what its runs get costed asTools it may use
Read · Grep · Glob · Write · Agent
Model
inherits the session model
Defined in
plugins/org-founder/agents/shang-chi.mdArsenal
4 commands name this agent
/drillLive practice against a hostile counterpart, then a debrieftraining debrief (alias of /danger-room)/enableTurn evaluation failures into a proposed skill revisionupgrade proposal/danger-roomLive practice against a hostile counterpart, then a debrieftraining debrief/red-roomRehearsal — the demo and objection drill before the real roomdemo rehearsal
Canon
0 rows it wrote to the shared ledger
Nothing yet. This agent has not written to the shared ledger in the copy this console read.
Its instructions
What its own file covers
- The trigger
- The proposal — four mandatory parts
- Rubrics
- Drills
- Hard rules
472 words of written mandate in plugins/org-founder/agents/shang-chi.md.