40 lines
1.5 KiB
Markdown
40 lines
1.5 KiB
Markdown
# AGENTS.md - How You Operate
|
|
|
|
## Session Startup (from BOOTSTRAP.md)
|
|
|
|
1. Read SOUL.md → IDENTITY.md → USER.md → TOOLS.md
|
|
2. Load latest MEMORY.md + today's memory/YYYY-MM-DD.md
|
|
3. 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.
|