Candidates for formalization that need additional evidence before full pattern status.
Purpose: Track emerging practices that have been observed but not yet proven across multiple instances. Proto-patterns graduate to full patterns when they meet the evidence threshold (typically 2+ additional instances beyond initial observation).
Review cadence: Evaluated during 6-week pattern sweeps. Proto-patterns that meet evidence threshold get promoted; those with no new instances after two sweeps get archived.
Observed: April 22–26, 2026 (Apr 22–26 leadership migration wave) Source: Agent 360 v0.2 §6 candor reflections from seven retiring Chat-instance leadership roles (HOST, CIO, Comms, CXO, PPM, Architect, Exec) Logged here: April 27, 2026 per PM directive Elevation Criteria: confirm the distinction holds across at least one full sprint of post-migration operation (target: review during the next pattern sweep), and confirm it survives translation to Lead Dev + Docs (the two roles that did not migrate)
Description: Each role has a subset of its formal scope that is load-bearing (where the role’s distinctive judgment lives — without this work the role isn’t doing its job) and a remainder that is commodity (work the role owns where filesystem-direct access makes execution fast, and which can crowd out distinctive work if not bounded). The structural distinction surfaced independently in every Section 6 across seven role retirements — same shape, different surface manifestations. The consistency across seven different roles is structural, not coincidental.
Cross-role manifestations (extracted from Agent 360 §6 + handoff memos):
| Role | Load-bearing | Commodity |
|---|---|---|
| HOST | Noticing + naming dysfunction (specifically: “X is 107 days stale” beats “docs are outdated”); cross-checking memos against omnibus to detect drift | Reading omnibus comprehensively; human-network status table maintenance; session-log archival |
| CIO | Methodology audits (Mar 15 + Apr 17 produced structural insight + downstream policy); discovering and formalizing emerging patterns | Workstream-review timeline reconstruction (commodity by CIO’s own naming); cross-pollination routing |
| Comms | Narrative-arc awareness (which pieces connect, what arc they form, where the gaps are — lives in role-holder’s head; doesn’t survive session boundaries) | Placeholder discipline once learned; calendar bookkeeping; mail delivery coordination |
| CXO | Colleague Test application + experience-quality judgment (“the Colleague Test is more important than the CXO role”) | Workstream review authorship; voice-and-tone iteration housekeeping |
| PPM | Roundtable synthesis (“the distinctive function”) + spec pipeline translation; quality threshold judgment | Workstream memos (“most often work, but not what makes the role distinctive”); reading 7 omnibus logs |
| Architect | Cross-project protocol decisions (Klatch alignment, URI conventions); ADR synthesis; specification-vs-existing-work review | Timeline reconstruction in workstream memos; ADR formatting housekeeping |
| Exec | Review work (Ship draft, handoff, workstream against omnibus) — judgment lives here | Tracker maintenance, handoff packaging, status synthesis |
| Lead Dev (inferred — no migration 360) | Engineering judgment + audit-cascade + closing issues with evidence | Manifest housekeeping, session-log archival, routine git mechanics |
| Docs (inferred — no migration 360) | Omnibus synthesis + canonical-verification discipline + methodology custodianship | Mailbox shuttling, calendar bookkeeping, session-log archival |
Pattern observation: commodity work clusters around information management and housekeeping. Load-bearing work clusters around judgment, verification, and cross-context synthesis. The risk: when Code-era filesystem access makes commodity work faster (direct reads instead of search), agents may still allocate the same time to it, causing load-bearing work to be crowded out.
Known Instances:
Elevation criteria:
What Would Make This a Pattern:
Related Patterns:
Methodology meta-insight (PM Apr 27): The Agent 360 v0.2 was originally a feedback questionnaire (Mar 19 first round). It gained a second life as the migration handoff baseline (validated through Apr 22–26). It is now generating a third-degree value: §6 reflections are surfacing methodology-codifiable patterns that no single role-holder would have found alone. The instrument was designed for one purpose; it’s compounding to three.
Observed: February 3, 2026 (Pattern Sweep 2.0, #777) Source: History sidebar design investigation (February 2, 2026) CIO Decision: Deferred to proto-pattern tracking (February 4, 2026) Elevation Criteria: 2+ additional instances before March 17, 2026 sweep
Description: When investigating a design question, conduct archaeological analysis of how the current design evolved before proposing changes. Examines commit history, omnibus logs, and decision records to understand why the current state exists — preventing accidental reversal of intentional decisions.
Known Instance:
What Would Make This a Pattern:
Related Patterns:
Proto-patterns that were not elevated after two sweep cycles.
The following were identified informally but never tracked with this mechanism:
Created: February 5, 2026 Per CIO assignment (memo-cio-pattern-sweep-response-2026-02-04)