Nightly context trim for ACTIVE_PRIORITIES and the dated SESSION_LOG schema. Archives before removal, uses content-hash compare-and-swap, and refuses unknown shapes.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
This is the sole bounded compaction exception to the Session Log chronicle. It runs only when invoked, never while the framework is being installed or tested against a real vault.
vault/memory/SESSION_LOG.md and
vault/memory/ACTIVE_PRIORITIES.md.node daemons/nightly-context-hygiene.mjs --root <aigent-root>
Green means no edit is needed. Red permits only the bounded archive below. Unreadable or unfamiliar content is a failure, not permission to rewrite.
The executable target schema uses newest-first dated H2 blocks. A canonical
block starts with ## YYYY-MM-DD - title and contains one nonempty occurrence
of each field:
ObjectiveCompletedDecisionsOpen threadsNext actionArchival rules:
vault/memory/SESSION_LOG_ARCHIVE_<YYYY-MM-DD>.md.The mechanically checkable live shape contains:
## Operating Mode: <mode> heading;## Tier 1, ## Tier 2, or
## Tier 3 headings;Last reviewed: YYYY-MM-DD line; and## Archived section.Move only content explicitly marked stale, superseded, or archived to
vault/memory/ACTIVE_PRIORITIES_ARCHIVE_<YYYY-MM-DD>.md. If removal requires a
human decision, preserve it and report the gate.
Immediately before each write, hash the live source again. If either hash
differs from the precondition hash, abort with CONTEXT_HYGIENE_RACE. Archive
must be durable before the source is trimmed.
After writing, re-run the checker. Only its literal
CONTEXT_HYGIENE PASS receipt may record the checkpoint green. Return archive
paths and before/after hashes in bounded detail. Never touch another memory
file.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
The English summary is being prepared. Showing the original description.
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
The English summary is being prepared. Showing the original description.
Generate a structured delegation brief for any task
The English summary is being prepared. Showing the original description.
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
The English summary is being prepared. Showing the original description.
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
The English summary is being prepared. Showing the original description.
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
The English summary is being prepared. Showing the original description.