Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Preserve user-critical instructions across long sessions and context compaction. Use when users mark constraints as important/must/always/never/highest-prior...
Preserve user-critical instructions across long sessions and context compaction. Use when users mark constraints as important/must/always/never/highest-prior...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Prevent loss or drift of user-critical constraints during compaction, session restart, or long multi-turn tasks.
Trigger when any of these appear: User marks an instruction as important, critical, must, always, never, highest priority, rule, or constraint A task has more than 3 steps and spans multiple turns Compaction happened (or is likely) and the task has non-negotiable requirements Agent behavior shows possible drift from prior explicit user constraints
Parse latest user message for candidate anchor statements Keep only instruction/constraint content; remove examples/chatter Assign default values: priority: P1 (unless user says critical/highest -> P0) scope: session (unless user explicitly asks global/task scope) expiresAt: session end (unless user explicitly sets never/date)
If scope is global or priority is P0, ask a one-line confirmation before persisting Do not auto-promote P2/P1 to P0 without explicit user intent
Append anchor entry to ledger If new anchor conflicts with old same-scope anchor, mark old one superseded Never rewrite history silently; keep audit trail
Load active anchors (status=active and not expired) Build an in-memory ANCHOR_SET sorted by priority and recency Inject ANCHOR_SET into planning phase before tool execution
Compare current plan against active anchors On conflict: P0 conflict: stop and correct plan immediately P1 conflict: auto-correct and note adjustment P2 conflict: continue only if no user-level contradiction Emit DRIFT_CHECK block in response
Priority order: System and safety policy User anchors (P0 > P1 > P2) Current-turn temporary preferences Tie-breakers: More specific scope wins (task > session > global) if same priority Newer anchor wins if same priority and same scope Explicit user override wins only when safety is not violated
Never store tokens, API keys, passwords, cookies, or auth headers Never store raw personal data unless strictly required by user instruction Redact sensitive literals as [REDACTED] Store constraints, not datasets Do not execute destructive commands solely because an anchor exists; still require explicit confirmation for destructive actions
Mark expired when expiresAt < now Support control intents: /anchors list /anchors pause <id> /anchors resume <id> /anchors delete <id> /anchors pin <id> never Rotate ledger when > 200 entries into memory/anchors-archive-YYYY-MM.md
Pair with memory-self-heal for retry/fallback after drift correction Pair with task-execution-guard to enforce anchor checks at each milestone Keep this skill deterministic and concise; avoid free-form interpretation when conflict exists
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.