David F GliddenandClaude Opus 4.8
3f9a89b00c
Basic Memory v0.21.6 first sync over the live memory dir (steward-authorized live-dir trial, Option A 2026-06-06): adds permalink: to frontmatter, refolds long YAML description lines, strips final newlines. Bodies untouched — verified via full diff classification. From this commit forward, any diff in claude/memory shows only what Basic Memory or the session writes. Trial design: MemPalace untouched as incumbent; git status check on this dir at every wrap; end-of-day evaluation (recall quality, sync robustness, rebuild-from-files, malformed-file behavior). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
28 lines
2.6 KiB
Markdown
28 lines
2.6 KiB
Markdown
---
|
|
name: Standing authorization to invoke specialist sub-agents with Symmetria
|
|
description: 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.
|
|
type: feedback
|
|
originSessionId: a3ddbf34-da48-4129-acba-658f2f869783
|
|
permalink: claude-memory/feedback-independent-specialist-authorization
|
|
---
|
|
|
|
# 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). |