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/cruftgit clone --depth 1 https://github.com/mindroom-ai/mindroomWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/mindroom-ai/mindroom/cruft)<a href="https://agentmods.dev/commands/mindroom-ai/mindroom/cruft"><img src="https://agentmods.dev/badge/commands/mindroom-ai/mindroom/cruft.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00013 | $0.00767 |
| Opus 5 | $0.00006 | $0.00383 |
| Sonnet 5 | $0.00003 | $0.00153 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
cruft scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anti-Cruft Review
CRITICAL: Scope Analysis
Current feature diff from main:
!git diff origin/main
⚠️ STRICT SCOPE LIMITATION ⚠️
ONLY modify code that is part of the current feature shown in the diff above!
- If a file doesn't appear in the diff, DO NOT TOUCH IT
- Only remove cruft from files that are already being modified
- Focus exclusively on the current feature's code
- Leave all other code untouched, even if it has cruft
Review Target
Review the code at @$ARGUMENTS and ensure it follows MindRoom's core philosophy from CLAUDE.md:
MANDATORY Principles to Enforce:
1. NO Backward Compatibility
- This project has ZERO users - break anything that needs breaking
- Remove ALL fallback code paths
- Delete compatibility shims, version checks, deprecated methods
- One way to do things, not multiple
2. Radical Simplicity
- Functional over classes: Simple functions, not inheritance hierarchies
- Prefer dataclasses: Typed dataclasses over dicts
- No over-engineering: Solve TODAY's problem, not tomorrow's
- No defensive programming: Assume correct usage - no redundant checks
3. Code Hygiene
- Imports at the top: NEVER in functions (except circular import fixes)
- No unnecessary try-except: Only catch what can actually fail
- Remove unused code: Functions, imports, variables - delete ruthlessly
- No premature abstraction: Concrete implementations first
- NO DUCKTYPING: Explicit is better than implicit, so no
hasattrorgetattr, just use proper types withisinstancechecks if needed
Check for Common Cruft:
-
Fallback patterns to DELETE:
if x else default_fallbackwhen x should always existtry/except: passhiding real issues- Multiple ways to configure the same thing
- "Just in case" code paths
-
Over-engineering to REMOVE:
- Abstract base classes
- Complex inheritance chains
- Factory patterns for simple objects
- Unnecessary interfaces/protocols
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.
- 6d ago First seen · 80 lines · 13 tokens per session scan A d1c1956278c3
cruft is a command published in the GitHub repository mindroom-ai/mindroom (260 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 767 once invoked, about $0.0001 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.