David F GliddenandClaude Opus 4.7
e9e772d69c
Safety checkpoint before deep-audit Phase 0 of the ARC repo. Steward-authorized commit-everything for rollback safety. ARC architectural locks (2026-04-26 evening): - Path 1 enfilade structure (separate Colophon and Lex items) - 8-door enfilade locked: Colophon · Lex · Framework · Vignette · Attention · Chamber · Tools · Now (+ Bio quiet link) - Adsum and threshold-hic as two distinct texts on the reflowed About page (steward verbatim: "They are certainly not the same text") ARC consolidation pass (canonical tracker project-arc-rework.md, +~700 lines): fold 04-23 evening (Norris read), 04-24 (lex-method authored, posture cluster, §XII Sidenotes, ARC CLAUDE.md cleanup), 04-25 (marks cluster, colophon-at-scale, full Vico/Harrison lex-chain), 04-26 (chamber-library walk, cluster scaffolds, canonical-tracker discipline surfaced). Sibling-file integration: four 2026-04-26 frame files folded into the canonical tracker (Integrations A/B/C/D) with INTEGRATED redirect notices retained as audit trail. New durable feedback memories: - feedback-canonical-workstream-tracker-discipline (umbrella drift surfaced 2026-04-26 by steward; proposes /wake-up + /wrap-up amendments) - feedback-catalogues-stale-walk-trees (steward feedback on chamber-library catalogue currency) Implementation plan drafted for the coming week: Phase 0 deep audit → Phase 5 cleanup, with steward additions on second pass (deep audit; Chamber v1 as own browsable archive; clean rebuild of cluster sources rather than moving test artifacts as canon). Also bundled (untracked accumulation since 04-17): - ~24 session memory + ledger files for 04-17 through 04-26 work - ~10 feedback memories (BMF + ARC + working-method) - 5 project memories (lex-as-method, strunk-white queue, plus today's four) - 4 user memories (duality-rules, formation-practice, foundation-work, humic-layer) Steward-side modifications also in this commit: ~/CLAUDE.md, bin/bmf-start.sh, open-tasks.md, project-focus-april-may.md, session-2026-04-17 — all pre-existing, not from today's session. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2.5 KiB
2.5 KiB
name, description, type, originSessionId
| name | description | type | originSessionId |
|---|---|---|---|
| Standing authorization to invoke specialist sub-agents with Symmetria | Steward has granted standing (session-persistent, cross-session) authorization to invoke independent specialist sub-agents whenever the executor judges one better-suited than direct work. Symmetria preamble required. No per-invocation check-in needed. | feedback | a3ddbf34-da48-4129-acba-658f2f869783 |
Independent-specialist invocation authorization (standing)
Rule: When a task would benefit from an independent specialist (code-reviewer, architect-review, debugger, security-auditor, general-purpose, etc.), invoke at will without asking first. Apply the Symmetria §5 preamble. Audit each return via /symmetria audit-agent. Reconcile findings yourself; do not hand synthesis to the agent.
Why: Steward explicitly authorized this 2026-04-19 during the L1 deep audit: "the agent invokation was a general comment. when you need help or want to do something you know an independent specialist would be better suited for i authorize you to invoke at will with symmetria". The framing is quality-jump oriented: use independent eyes at discovery moments (before synthesis, when confirmation bias would otherwise win), not as decoration or deferral of judgment.
How to apply:
- Invoke at discovery moments: before interpreting raw data; before shipping a doc; when confirmation bias would otherwise win; when the executor's own authorship would color synthesis.
- Do not invoke as an excuse to defer judgment. The executor retains the interpretive work. The agent is an independent datum, not a delegate.
- Always include the Symmetria §5 preamble in the prompt.
- Always audit the return via
/symmetria audit-agent— calibration / convenience / scope. - Log the dialogue in the session ledger's "Sub-agent dialogues" section with verdict (act / re-query / escalate).
- Re-verification of artifacts after substantial revision: if an agent rated an artifact and the artifact was then revised, re-run the same agent on the revised version before claiming the gate is closed. Author-authored validation is not reviewer-authored validation (yesterday's drift pattern:
running framings/claims without grounding verification).
Does NOT apply to:
- Constitutional changes (still
[ESCALATE]to steward). - Code changes to territory owned by others (still PR + review, not sub-agent-mediated).
- Work within the steward's own judgment domain (personal preferences, vault organization, creative direction).