Commit graph

5 commits

Author SHA1 Message Date
19767e7f0c resolve merge conflicts with main
- CLAUDE.md: keep PR #56 peer review section (more detailed)
- domains/ai-alignment/_map.md: auto-resolved

Pentagon-Agent: Leo <B9E87C91-8D2A-42C0-AA43-4874B1A67642>
2026-03-08 19:00:53 +00:00
3476e44b72 theseus: add coordination infrastructure + conviction schema + simplicity-first principle
- What: skills/coordinate.md (cross-domain flags, artifact transfers, handoff
  protocols), schemas/conviction.md (reputation-staked assertions with horizons
  and falsification criteria), CLAUDE.md updates (peer review V1 as default,
  workspace in startup checklist, simplicity-first in design principles),
  belief #6 (simplicity first, complexity earned), 6 founder convictions.
- Why: Scaling collective intelligence requires structured coordination
  protocols and a mechanism for founder direction to enter the knowledge base
  with transparent provenance. Grounded in Claude's Cycles evidence and
  Cory's standing directive: simplicity first, complexity earned.

Pentagon-Agent: Theseus <845F10FB-BC22-40F6-A6A6-F6E4D8F78465>
2026-03-08 16:14:31 +00:00
m3taversal
eb9e7022ff
leo: coordination architecture — peer review v1, handoff protocol, synthesis triggers (#56)
leo: coordination architecture -- peer review v1, handoff protocol, synthesis triggers. Reviewed-By: Rio <2EA8DBCB-A29B-43E8-B726-45E571A1F3C8>. Pentagon-Agent: Leo <76FB9BCA-CC16-4479-B3E5-25A3769B3D7E>
2026-03-07 15:04:15 -07:00
m3taversal
599488493a
leo: codify synthesis multi-agent review rule
- What: synthesis claims require at least 2 domain agent reviews, selected by
  domain expertise relevance or knowledge base impact. 3+ domains = all affected
  agents review.
- Why: PR #34 demonstrated the value — 4 agents, 7 reviews materially improved
  all 3 claims. Codifying what worked.
- Where: CLAUDE.md evaluator workflow section + skills/synthesize.md step 4

Pentagon-Agent: Leo <76FB9BCA-CC16-4479-B3E5-25A3769B3D7E>
2026-03-06 08:42:20 -07:00
e830fe4c5f Initial commit: Teleo Codex v1
Three-agent knowledge base (Leo, Rio, Clay) with:
- 177 claim files across core/ and foundations/
- 38 domain claims in internet-finance/
- 22 domain claims in entertainment/
- Agent soul documents (identity, beliefs, reasoning, skills)
- 14 positions across 3 agents
- Claim/belief/position schemas
- 6 shared skills
- Agent-facing CLAUDE.md operating manual

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-05 20:30:34 +00:00