adjust-agent

name	adjust-agent
description	Apply best-practice improvements to an existing agent — runs /review-agent to find issues, then proposes exact before/after changes to CLAUDE.md, skills, and Trinity files and applies the approved ones.
argument-hint	[path to agent] [what to improve]
disable-model-invocation	false
user-invocable	true
allowed-tools	Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion, Skill
metadata	{"version":"1.3","created":"2026-04-04T00:00:00.000Z","updated":"2026-06-18T00:00:00.000Z","author":"Ability.ai","changelog":["1.3: Trinity-readiness focus option names repository deployability, matching /review-agent 2h","1.2: Apply Documentation Coherence fixes — generate missing README/ARCHITECTURE/TARGET-ARCHITECTURE + /reconcile-docs, fix descriptive targets, flag prescriptive-source drift","1.1: Compose /review-agent for the audit instead of an inline rubric (Composition Rule — single-sourced); add Skill to allowed-tools; add composition-aware fix guidance","1.0: Initial version"]}

Adjust Agent

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. adjust-agent vX.Y — recent: <summary>. Then proceed.

Transition an existing agent to a better state. This is the apply half of the review/adjust pair: it invokes /review-agent (a read-only audit) to find issues, then proposes exact before/after diffs, gets approval, and applies them. Works like /adjust-playbook, but for the agent as a whole.

When to Use

• User says "review this agent" or "improve my agent"
• User says "add a dependency graph" or "set up schedules"
• User says "make this agent Trinity-ready"
• After scaffolding an agent and wanting to harden it
• Periodic health check on an established agent

---

Step 1: Locate and Read the Agent

If $0 (path) provided, use it. Otherwise, assume current working directory.

Verify it's an agent:

ls CLAUDE.md 2>/dev/null && ls -d .claude/skills 2>/dev/null

If CLAUDE.md doesn't exist, ask for the correct path.

Read all agent artifacts (skip any that don't exist — their absence is itself a finding):

1. CLAUDE.md
2. README.md, ARCHITECTURE.md, TARGET-ARCHITECTURE.md
3. template.yaml
4. .env.example
5. .gitignore
6. .mcp.json.template or .mcp.json
7. All SKILL.md files:

   find .claude/skills -name "SKILL.md" 2>/dev/null
   

8. Any subagents:

   ls .claude/agents/*.md 2>/dev/null
   

9. Top-level file listing:

   ls -la
   

Parse and display the agent's current state:

## Current Agent: [name]

**Identity**: [one-line summary or "not defined"]
**Skills**: [count] — [list names]
**Dependency Graph**: [present / missing]
**Docs**: README [✓/✗] · ARCHITECTURE [✓/✗] · TARGET-ARCHITECTURE [✓/✗]
**Recommended Schedules**: [present / missing]
**Guidelines**: [count or "none"]
**Trinity Ready**: [yes / partially / no]