Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/mindroom-ai/mindroom/initgit clone --depth 1 https://github.com/mindroom-ai/mindroomWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00005 | $0.00985 |
| Opus 5 | $0.00003 | $0.00492 |
| Sonnet 5 | $0.00001 | $0.00197 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize MindRoom Understanding
Your Task
$ARGUMENTS
Instructions:
- If a feature description was provided above, initialize your understanding of MindRoom and then start implementing that feature
- If no feature description was provided (empty above), just initialize your understanding and wait for further instructions
- Either way, first understand the current development context and project structure below
Current Development Context
- Current branch: !
git branch --show-current - Changes from main: !
git diff origin/main --stat - Full diff: !
git diff origin/main
Note: If there are no changes from main, we're starting fresh. Otherwise, understand the current feature being developed from the diff above.
Important: Speech-to-Text Usage
The user often dictates using speech-to-text, so expect:
- Typos and incorrect words
- Imperfect sentence structure
- Homophone substitutions (e.g., "to/too/two", "there/their")
- Missing punctuation or capitalization
Focus on understanding the intent rather than the exact wording. When in doubt, clarify rather than assume.
Project Understanding
Read and understand the MindRoom project structure:
-
Read Core Documentation
- Full README.md for project purpose and architecture
- CLAUDE.md for development guidelines and workflow
-
Code Structure
- Main bot:
src/mindroom/bot.py - Matrix interactions:
src/mindroom/matrix/modulematrix/client.py- Core Matrix client functionsmatrix/mentions.py- Mention handlingmatrix/message_builder.py- Message constructionmatrix/identity.py- Matrix ID handlingmatrix/rooms.py- Room managementmatrix/state.py- State managementmatrix/users.py- User management
- Main bot:
-
Development Best Practices
- ALWAYS check for existing helper functions before implementing new ones
- Look in
matrix/module for Matrix utilities - Check
thread_utils.pyfor thread handling - Review
commands.pyfor command patterns - Use uv (not conda) for package management
- Install:
uv sync --all-extras - Activate:
source .venv/bin/activate - Add packages:
uv add <package>oruv add --dev <package> - Critical Git practices:
- NEVER use
git add .- always add files individually - Always run
pytestbefore claiming completion - Run
pre-commit run --all-filesbefore commits
- NEVER use
- Code style:
- Prefer functional style over classes
- Use dataclasses over dictionaries
- Keep it DRY - aggressively remove unused code
- Don't wrap in try-except unless necessary
- Imports at top of file (except for circular imports)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 99 lines · 5 tokens per session scan A ab8a6d9cd311
init is a command published in the GitHub repository mindroom-ai/mindroom (254 stars, last pushed 2d ago), licensed Apache-2.0. It adds 5 tokens to every session and 985 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.