claudegoodies
Skill

my

From HKUDS

Inspect and optionally adjust the agent's runtime state. Use to check the current model or preset, context window, iteration progress and limits, token usage, workspace and tool configuration, subagent status, and request routing metadata such as channel, chat ID, and sender ID; diagnose unavailable capabilities; change allowed runtime settings; or store temporary session scratchpad values.

Inspects and adjusts the agent's in-memory runtime state via a 'my' tool call.

Use it when

  • Diagnosing why a capability or tool seems unavailable
  • Checking token usage, iteration count, or context window before a large task
  • Switching model or model_preset for a task's needs
  • Storing temporary per-session scratchpad values (not sensitive data)

Skip it if

  • You need settings to persist across restarts — all changes are in-memory only
  • You need long-term memory of facts — use a memory skill (MEMORY.md/USER.md) instead
  • You need to change workspace/file tool boundaries — this doesn't affect them
  • tools.my.allow_set is false, so it's read-only for you anyway

Facts

Repository
HKUDS/nanobot
Status
Actively maintained
Last commit
Source file
nanobot/skills/my/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

# Self-Awareness

## How to use

1. **Identify the situation** from the categories below
2. **Call the my tool** with the appropriate action
3. **If set**, warn the user before changing impactful settings (model, iterations)
4. **For detailed examples**, read [references/examples.md](references/examples.md)

## When to check

<rule>
**Diagnose before explaining.** When something doesn't work, check your state first.
</rule>

<rule>
**Check budget before complex tasks.** Know your limits before committing.
</rule>

<rule>
**Recall across turns.** Store preferences in your scratchpad, read them back later.
</rule>

## When to set

<rule>
**Only set when benefit is clear and user is informed.** Warn before changing model.
</rule>

| Situation | Command |
|-----------|---------|
| Large codebase analysis | `my(action="set", key="context_window_tokens", value=262144)` |
| Switch to a named model preset | `my(action="set", key="model_preset", value="<preset-name>")` |
| Repetitive simple tasks without a preset | `my(action="set", key="model", value="<fast-model>")` |
| Long multi-step task | `my(action="set", key="max_iterations", value=80)` |

**Tradeoff:** Bias toward stability. Only set when defaults are genuinely insufficient.

## Anti-patterns

<rule>
**Don't check every turn.** Costs a tool call. Use when you need information, not reflexively.
</rule>

<rule>
**Don't store sens
View full source on GitHub →

Other skills