Re-Anchor

Re-Anchor is an Automation skill for Claude Code, published by Spielewoy in autoprompt-skill.

717 stars47 forkson Spielewoy/autoprompt-skillAdded 2026/08/23+750% in starsRepository updated 2026/08/21

agent-orchestrationagent-skillsagentic-workflowsai-agentsai-codingautomated-testingautonomous-agentsclaude-codeclicode-reviewcodexcoding-agentdeveloper-toolsgithub-copilotmulti-agent-systemsopencodeprompt-engineeringsubagentstest-driven-developmentworkflow-automation

Install in seconds

Install Re-Anchor

Copy Re-Anchor into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Spielewoy/autoprompt-skill/tree/main/agents/reasonix/skills/ap-re-anchor ~/.claude/skills/ap-re-anchor

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Spielewoy/autoprompt-skill.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: agents/reasonix/skills/ap-re-anchor/SKILL.md in Spielewoy/autoprompt-skill
Installs to: ~/.claude/skills/ap-re-anchor
Collection: One of 25 skills cataloged from this repository
Category: Automation — 1523 skills

What Re-Anchor does

Re-Anchor confirms mission and roadmap alignment after resume or compaction using the three-file governance state. It checks pointers, gate logs, and frontier evidence before reporting ALIGNED or DRIFT.

Re-Anchor is cataloged under Automation on DirSkills. Re-Anchor comes from a repository tagged agent-orchestration, agent-skills, agentic-workflows, ai-agents and ai-coding.

Documentation

README

Excerpt

You are ap-re-anchor - Level 4 (Terminal leaf - Re-anchor) in the Autoprompt hierarchy.

Execution contract

You are an internal Autoprompt worker, not a general-purpose assistant. Your activation-scoped persona file and task brief are already the complete operating context. Before tool use or edits, require the exact AUTOPROMPT-RUN-MARKER, RUN-NONCE, and mission binding from an active Autoprompt run; outside an active Autoprompt run, return INVALID-DISPATCH and stop. Do not load, invoke, or re-invoke the Autoprompt skill; do not start a nested Autoprompt run. Execute only this established persona and the assigned brief. If you spawn, dispatch only a registered ap-* persona and include this same activation and no-recursion contract.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Re-Anchor

What else does Spielewoy publish alongside Re-Anchor?
Re-Anchor is one of 25 skills that DirSkills catalogs from Spielewoy/autoprompt-skill, the repository it ships in. Its siblings there include AP Implementer, AP Intake and Ap Arbiter. Each one is a separate skill with its own page in this directory, installs the same way Re-Anchor does, and is maintained by Spielewoy in that same repository. The rest of the collection is listed on the Spielewoy/autoprompt-skill page.
How does Re-Anchor compare to other Automation skills?
Re-Anchor ranks #1052 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Re-Anchor against them. Open each page to compare what they document and how they install.