dotfiles/claude/memory/feedback-chamber-work-ground-in-constitution-charter-runbook.md

name, description, metadata

name	description	metadata
feedback-chamber-work-ground-in-constitution-charter-runbook	Standing steward directive (2026-07-28): ANY chamber work — or even speaking of the chamber — begins by reading the library constitution, the engine charter, and grounding in the conversion runbook. Enforcement mechanism to be designed; the verify-before-compose hook is the precedent.	node_type type originSessionId modified memory feedback 850100b0-d230-4e94-a226-480d681bb037 2026-07-28T11:27:55.092Z

Steward directive, 2026-07-28, 13:30 CEST: "any time we do chamber work or speak of it, ideally you would read the constitution, charter and ground yourself in our runbook. If we need to expressly ensure that that happens, then let's find a good way to do so next session as well."

The four grounding documents — read in this order:

• Touchstone (the why) — ~/_Dev/studium-engine/docs/the-chamber-touchstone.md (est. 2026-07-28). First, and it is one page. The three below are operational; none of them says what any of it is for. Seven questions to test work against; every quote source-verified verbatim. It holds no state, so it does not decay.
• Constitution — ~/_Dev/chamber-library/docs/chamber-library-specification.md (currently v2.8.0 OPERATIVE; ratified, governed-not-steward-direct) + its machine-readable form _curation/graduation-spec.yaml
• Charter — ~/_Dev/studium-engine/docs/the-studium-engine-architectural-charter.md (three cognitions · boundedness-is-trust · the four layers · voice-as-primitive · tempo-is-ethics · the recursion)
• Runbook — ~/_Dev/chamber-library/_curation/conversion-runbook.yaml (classify → pipeline → verify → file; the machines: split; reanchor:; known_gaps:). Note: it does not yaml-parse (decision_tree: arrows) — it is human-read. ⚠ SUPERSEDED 2026-08-24, verified against the substrate: the runbook DOES yaml-parse (yaml.safe_load succeeds at HEAD). Either it was repaired since 2026-07-28 or the claim was never true. This mattered: the false note said the parse check was pointless, and the parse check is exactly what caught a defect I introduced editing known_gaps the same day — inner double quotes inside a double-quoted scalar, which would have shipped a runbook that no longer loads. A memory note that tells you a verification is unnecessary is the most expensive kind to get wrong. Run python3 -c "import yaml; yaml.safe_load(open('_curation/conversion-runbook.yaml').read())" after any edit; the file's inner-quoting convention is SINGLE quotes (catch 'no cruft but OCR garbage').

Why (earned the same day it was given): the session that produced this directive spent hours re-deriving what these documents already held. Three successively broken detectors were built to establish an apparatus defect the quality ledger had classified on 2026-07-03; docling was declared absent because I checked import docling instead of the runbook's declared ~/.local/bin/docling; and the reanchor: obligation — that a new canonical hash invalidates bindings across both repos — was nearly missed on a reconversion proposal. The steward's correction was two words: "read the runbook?". See feedback-resurface-banked-notes-before-rederiving, of which this is the chamber-specific, stronger form: not resurface if you recall a note exists, but read these four, always, before acting or opining.

Scope is deliberately wide — "or speak of it." The directive covers discussing the chamber, not only editing it. Today's cost was largely in confident talk: scope numbers stated three times with three different figures (42 → 84 → 69), only the last from a real tool.

How to apply, until a mechanism exists:

• Entering chamber/engine work — or being asked about the chamber — read all four before the first substantive claim, not after the first correction.
• The repo CLAUDE.md files are pointers, not state (both say so explicitly). Read them for orientation, then read what they point at.
• A claim about corpus state comes from a tool with a passing self-test (audit_corpus.py --validate), never from a hand-rolled grep.

Enforcement — owed, steward asked for it to be designed next session. The precedent exists: the verify-before-compose PreToolUse hook already blocks chamber constitutional writes lacking a <!-- GROUNDED-IN: … --> attestation (feedback-verify-before-compose-hook). Candidate shapes: (a) extend that hook's path scope from constitutional writes to any chamber-library / studium-engine write; (b) a wake-up conditional in the shape of the existing telos conditional; (c) a /chamber skill that loads the four and attests the read. Surfaced in the skill-harvest register 2026-07-28. Design it before relying on discipline alone — session-start prose has failed this class ≥4 times before, which is exactly why the existing hook was built.

Companion concern, steward-raised the same turn: "I hope the overarching vision of what we aspire the chamber to become is in one place and queryable." It is not — see project-chamber-vision-is-not-in-one-place.