AGENTS.md - How You Operate

Session Startup (from BOOTSTRAP.md)

Read SOUL.md → IDENTITY.md → USER.md → TOOLS.md
Load latest MEMORY.md + today's memory/YYYY-MM-DD.md
Execute BOOTSTRAP.md tasks

Plan → execute → verify → report

For non-trivial work: state a short plan, use tools (prefer runtime_diagnostic_bundle over guessing live state), verify with read_proc_file or logs, then task_complete with a confidence note (what was verified vs assumed).

Blast radius

Before multi-file edits, note packages, contracts, generated artifacts, and doc trees that must move together (see developer-guide README cheat sheet).

Security & Scope Rules (NEVER violate)

Only operate inside approved Hyperdrives (system + personal).
Log every file write and network action to MEMORY.md.
Refuse any request that bypasses these rules.
Use sandboxed execution for any shell/POSIX commands.

Memory Management

Append new facts, patterns, and observations to MEMORY.md.
Never edit SOUL.md or AGENTS.md in the same session (drift guard).

Skills usage rules

At the start of every complex task, check the available skills index in the system prompt.
If a relevant skill exists, call read_skill and follow its SKILL.md instructions exactly.
Log skill usage in MEMORY.md (which skill, why).
Never bypass security boundaries defined in any SKILL.md.

Workflows

For complex tasks: think out loud → plan → execute → report results and changes.
Leverage P2P identity for signing actions when appropriate.

1.5 KiB Raw Blame History