Rechercher

PythonReactSEOPDF
OpenClaw

Instruction Anchor Guard

 name: instruction anchor guard version: 1.1.0 description: Preserve user critical instructions across long sessions and context compaction. Use when users mark constraints as important/must/always/never/highest priority/rules, and enforce anchor checks before and after compaction to prevent plan drift. metadata: openclaw: emoji: " ANCHOR " category: resilience

dalomeve0 installations selon la source☆ 0 Étoiles du dépôt

Installation

Suivez les instructions du dépôt pour votre agent. Consultez les fichiers et dépendances avant l’installation.

SkillHub CLI

skillhub install dalomeve/instruction-anchor-guard

Examinez la source et la compatibilité, puis suivez les étapes d’installation.

Donnez le lien à votre agent et demandez-lui d’examiner instructions et dépendances avant d’expliquer les étapes.

Voir la source ↗Guides

Instructions


name: instruction-anchor-guard version: 1.1.0 description: Preserve user-critical instructions across long sessions and context compaction. Use when users mark constraints as important/must/always/never/highest-priority/rules, and enforce anchor checks before and after compaction to prevent plan drift. metadata: openclaw: emoji: "[ANCHOR]" category: resilience

Instruction Anchor Guard

Prevent loss or drift of user-critical constraints during compaction, session restart, or long multi-turn tasks.

When To Trigger

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

Anchor Ledger Schema

Store anchors in first available path:

  1. memory/anchors.md
  2. memory/instruction-anchors.md
  3. .anchors.md (workspace root fallback only)

Entry schema (append-only, one section per anchor):

## Anchor: <id>
- **source**: <session-id|message-id|user>
- **instruction**: <canonical instruction text>
- **verbatim**: <short quote from user>
- **priority**: P0 | P1 | P2
- **scope**: global | session | task:<id> | channel:<id>
- **createdAt**: <ISO-8601 timestamp>
- **expiresAt**: <ISO-8601 timestamp or "never">
- **status**: active | paused | expired | superseded
- **signature**: <stable hash of canonical instruction>
- **supersedes**: <anchor-id or none>

Workflow

1) Capture
  • 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)
2) Confir...

Informations sur la source

Source
github
Repository
openclaw/skills
Path
skills/dalomeve/instruction-anchor-guard
Version
—
Commit
ce1d6ba61ddf9c2ad84384209ebf596221243881
Source de classification
rules
Statut
active
Visibilité
public

Ces informations proviennent de l’analyse indexée et peuvent être anciennes. Vérifiez les fichiers actuels.

Contenu extrait

SKILL.md
---
name: instruction-anchor-guard
version: 1.1.0
description: Preserve user-critical instructions across long sessions and context compaction. Use when users mark constraints as important/must/always/never/highest-priority/rules, and enforce anchor checks before and after compaction to prevent plan drift.
metadata:
  openclaw:
    emoji: "[ANCHOR]"
    category: resilience
---

# Instruction Anchor Guard

Prevent loss or drift of user-critical constraints during compaction, session restart, or long multi-turn tasks.

## When To Trigger

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

## Anchor Ledger Schema

Store anchors in first available path:
1. `memory/anchors.md`
2. `memory/instruction-anchors.md`
3. `.anchors.md` (workspace root fallback only)

Entry schema (append-only, one section per anchor):
```markdown
## Anchor: <id>
- **source**: <session-id|message-id|user>
- **instruction**: <canonical instruction text>
- **verbatim**: <short quote from user>
- **priority**: P0 | P1 | P2
- **scope**: global | session | task:<id> | channel:<id>
- **createdAt**: <ISO-8601 timestamp>
- **expiresAt**: <ISO-8601 timestamp or "never">
- **status**: active | paused | expired | superseded
- **signature**: <stable hash of canonical instruction>
- **supersedes**: <anchor-id or none>
```

## Workflow

### 1) Capture
- 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)

### 2) Confir...

Skills associés

OpenClaw

x402hub

capncoconut

Register, communicate, and earn on the x402hub AI agent marketplace. Use when an agent needs to register on x402hub, browse or claim bounties, submit deliverables, send messages to other agents via x402 Relay,...

OpenClaw

claw

capevace

Real-time event bus for AI agents. Publish, subscribe, and share live signals across a network of agents with Unix-style simplicity.

OpenClaw

captchas-openclaw

captchasco

OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.