Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or improve itself over time without becoming a multi-agent team.
SkillScore73Maintained
Automatic
◆AI Engineer pack
Last verified 8/17/2026
What it changes
Passed 16 of 22 test cases with the skill, and 5 of 22 without it.
Without skill23%
With skill73%
Checks it passed that the model alone missed
Uses Memory Tickets for durable state tracking.
Assigns project memory ownership to the PM Soul.
Includes .agentlas/global-commands.json in the package.
and 17 more in the full report
12 fixed4 passed either way5 still failing1 broke
Pass-rate lift
+50 pp
Tokens
+39%
Agent turns
0%
Response time
+19%
Model gemini-3.6-flashMeasured 8/17/2026v316 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
What specific configuration file inside the .agentlas directory manages external knowledge vault references for single-worker agents?
What was checked, without and with the skill
Checked
Without skill
With skill
Includes .agentlas/vault-references.json for external knowledge references.
Missed
Passed
case-16 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md33 linessingle file
Self-Evolving Single Agent
Procedure
Keep the package as one worker unless the user asks for a team.
Run contracts/builder-interview-research-gate.md before generation: ask an
8-12 question first batch, research official sources, similar agent
repositories or comparables, academic/professional theory, and plugin docs,
compare tool/plugin choices, and write the domain-expert synthesis plus
prompt-performance contract before creating the worker prompt.
Add memory architecture even for the single worker:
.agentlas/memory-map.json;
.agentlas/vault-references.json;
project memory owned by PM Soul/project owner;
Memory Events and Memory Tickets for durable updates.
If the task depends on current sources, add a research-refresh command,
watchlist memory section, references, and optional scheduled workflow.
Add docs/builder-interview.md, docs/research-sources.md,
docs/tool-selection.md, docs/domain-expert-synthesis.md,
docs/prompt-performance-contract.md, and
.agentlas/capability-eval-plan.json unless explicitly creating a minimal
private scaffold.
Make self-evolution proposal-first: draft patches or repair kits, then wait
for human approval before changing tools, connectors, secrets, or core
instructions.
Add .agentlas/global-commands.json and one public global command for the
worker across Claude Code, Codex, Gemini CLI, generic AGENTS.md, and
terminal adapters.
Output
Return agent_package, skills, memory_contract, refresh_loop,
approval_gate, global_commands, and verification.
Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.