Skip to main content
affpapa.org
RU EN
skill CX Codex

agent-plan-act-reflect — Claude Code skill: what it does

This deprecated skill remains relevant when old plans or prompts still name it. Learn which workflows need no skill and what replaces its unattended loop.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add WenyuChiou/agent-collab-skills --skill agent-plan-act-reflect -a claude-code
Open on GitHub

What agent-plan-act-reflect does

The skill was deprecated in 0.6.0 and removed in 0.7.0. A user-present cycle of editing code, running a check, fixing the result, and repeating needs no skill. Keep the acceptance check runnable and report its actual result.

For an unattended multi-cycle workflow under an agent-collab policy, use harness-loop.md. Run agent-collab policy evaluate after each cycle and before each agent spawn. Comparing two consequential alternatives belongs to agent-debate, not a loop. If an old plan still points to this skill, its instructions are out of date.

What it helps with

  • spot an outdated skill reference in a plan or prompt
  • tell a user-present check cycle from an unattended loop
  • move a policy-driven loop to harness-loop.md
  • route a comparison of alternatives to agent-debate

Example prompts for the agent

  • A plan names agent-plan-act-reflect. Explain which guidance is outdated and what should replace it.
  • Does agent-plan-act-reflect apply to editing code, running a check, and fixing the result?

How to install agent-plan-act-reflect

1Skills CLI (Vercel)

npx skills add WenyuChiou/agent-collab-skills --skill agent-plan-act-reflect -a claude-code

2Manually: put the files in place

~/.claude/skills/agent-plan-act-reflect/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agent-plan-act-reflect/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about agent-plan-act-reflect

How do I install agent-plan-act-reflect in Claude Code?

Run npx skills add WenyuChiou/agent-collab-skills --skill agent-plan-act-reflect -a claude-code. The skill file is at ~/.claude/skills/agent-plan-act-reflect/SKILL.md.

What does agent-plan-act-reflect do?

It is a deprecated stub. A normal cycle of edits and checks needs no skill; an unattended loop governed by an agent-collab policy uses harness-loop.md.

What replaces agent-plan-act-reflect for unattended loops?

Use harness-loop.md for an unattended multi-cycle workflow under a configured agent-collab policy. Run agent-collab policy evaluate after each cycle and before every agent spawn.

Source text

SKILL.md · MIT 
---
name: agent-plan-act-reflect
description: Use when a plan, prompt, or doc still names agent-plan-act-reflect. Deprecated in 0.6.0; ordinary iterate-until-it-passes work needs no skill, and an unattended policy-driven loop follows agent-context-budget's harness loop reference. This stub is removed in 0.7.0.
---

# agent-plan-act-reflect (deprecated)

Deprecated in 0.6.0 and removed in 0.7.0.

- Iterating with the user present (edit, run the check, fix, repeat) needs no
  skill. Keep the acceptance check runnable and report its real result.
- An unattended multi-cycle loop under a configured `agent-collab` policy
  follows [harness-loop.md](../agent-context-budget/references/harness-loop.md),
  the former body of this skill. It still runs `agent-collab policy evaluate`
  after every cycle and before every spawn.
- Comparing two consequential alternatives is
  [agent-debate](../agent-debate/SKILL.md), not a loop.

See [migration 0.6](../../docs/migration-0.6.md).

© WenyuChiou · MIT · WenyuChiou/agent-collab-skills

Similar skills

SKILL.md skills catalog →
find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. CX Codex +1 4,000,000installs frontend-design official anthropics This skill guides intentional visual design for new interfaces and redesigns. Use it when a generic generated UI is not enough. 1,025,790installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. 1,219,756installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs

From the same set5

agent-task-splitter Plans a fan-out of two or more subagents or CLI delegates on one goal: roles, model tiers, disjoint file scopes, capped returns. CX Codex +1 ★ 30repo stars agent-output-reconciler A stub for anyone whose plan or prompt still names the old skill. It points to the reconcile step inside agent-acceptance-gate. CX Codex +1 ★ 30repo stars agent-context-budget This skill bounds subagent replies, moves large outputs to files, and prepares handoffs when a session is nearing its context limit. CX Codex +1 ★ 30repo stars agent-acceptance-gate A read-only gate that reconciles parallel agent results and runs triggered checks before a commit or push. It returns PASS, CONDITIONAL PASS or FAIL with evidence. CX Codex +1 ★ 30repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor