Agent Centric

Track decisions (AGD) with validation and indexing. Use when making design decisions, recording important choices, discussing trade-offs, or when user mentions AGD or decision record.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add bolasblack/claude-skills --skill agent-centric
Manual install
git clone --depth 1 https://github.com/bolasblack/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/agent-centric ~/.claude/skills/agent-centric

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Agent Centric

Framework for agent-centric development. Currently provides AGD (Agent-centric Governance Decision) tracking.

## Required Setup Check

Before using this skill in a project, run the bundled read-only check. Resolve
`CLAUDE_SKILL_DIR` to the directory containing this `SKILL.md` and
`CLAUDE_PROJECT_DIR` to the target project root; supply these paths explicitly when
the host does not provide them.

```bash
python3 "${CLAUDE_SKILL_DIR}/scripts/check-setup.py" "${CLAUDE_PROJECT_DIR}"
```

Continue only when the command exits `0`. The check requires AGD configuration,
the decisions directory, and runtime scripts; an existing `.agents/` directory
alone is insufficient.

If the check fails or cannot run, **stop using this skill**. Briefly report the
missing setup and continue the user's task without AGD operations. Do not
initialize, sync, repair configuration, or create decisions/indexes to bypass the
check. Setup is a separate action: only follow [Setup](README.md#setup) when the
user explicitly requests it, then rerun this check.

After a successful check, sync the initialized project's managed files:

```bash
CLAUDE_PROJECT_DIR="${CLAUDE_PROJECT_DIR}" CLAUDE_SKILL_DIR="${CLAUDE_SKILL_DIR}" bash "${CLAUDE_SKILL_DIR}/scripts/sync-scripts.sh"
```

The sync respects `disableAutoUpdateScripts`. If files were updated, briefly inform
the user. Rerun the setup check on each skill load and whenever the target project
changes.

## What is AGD?
Read the full skill on GitHub

Details

Skill name
agent-centric
Path
skills/agent-centric/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Agent Centric skill do?

Track decisions (AGD) with validation and indexing. Use when making design decisions, recording important choices, discussing trade-offs, or when user mentions AGD or decision record.

How do I install the Agent Centric skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add bolasblack/claude-skills --skill agent-centric. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agent Centric popular?

It lives in bolasblack/claude-skills, which has 5 GitHub stars and 0 forks.

Related skills

Caveman

5

bolasblack/claude-skills

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

Images, Video & Audio

Codex

5

bolasblack/claude-skills

OpenAI Codex second opinion via the codex CLI — three modes. Review: independent diff review with a pass/fail gate. Challenge: adversarial pass that tries to break the code. Consult: ask Codex anything, with session continuity for follow-ups. Use when the user says "codex review", "codex challenge", "ask codex", or wants a second opinion from Codex.

Software Development

Command Creator

5

bolasblack/claude-skills

Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, custom prompt shortcut, or workflow automation command for Claude Code. Helps define command structure, frontmatter, arguments, and best practices.

AI, LLMs & Agents

Agent Retro

5

vnovakovits/claude-skills

Run a retrospective on a coding-agent session and improve the agent's environment, not the code. Combines Derby & Larsen's five-stage retrospective, Shigeo Shingo's poka-yoke (turn a mechanical mistake into a check that makes it impossible), and Matt Pocock's retro categories — navigation, automated checks, coding standards, steering files, tool economy, information access. Covers mining the session transcript for corrections, wrong turns and slow searches; deciding where each fix belongs (analyzer, hook, CI, reviewer standards, CLAUDE.md pointer, skill, doc or memory); the no-op test for stee

AI, LLMs & Agents

Write Prompt Guide

9

Lord1Egypt/RA-Skills

A distilled, model-aware checklist for writing high-quality prompts for Claude's latest models, built from Anthropic's prompt-engineering overview and best-practices docs (LaTeX guidance excluded).

AI, LLMs & Agents

AI Agents

8

Freddy-CHEN-ux/00_claude_skills

Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, and observability (modern best practices)

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.