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/railly/agent-brain/de-aigit clone --depth 1 https://github.com/Railly/agent-brainWhat 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 | $0.00013 | $0.00495 |
| Opus 5 | $0.00006 | $0.00247 |
| Sonnet 5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
de-ai 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.
What it actually says
De-AI-ify text: $ARGUMENTS
IMPORTANT: Be direct
- Read file, create -HUMAN version, apply changes
What Gets Removed
Overused Transitions
- "Moreover," "Furthermore," "Additionally," "Nevertheless"
- Excessive "However" usage
- "While X, Y" openings
AI Clichés
- "In today's fast-paced world"
- "Let's dive deep"
- "Unlock your potential"
- "Harness the power of"
- "Game-changer"
- "Cutting-edge"
Hedging Language
- "It's important to note"
- "It's worth mentioning"
- Vague quantifiers: "various," "numerous," "myriad"
Corporate Buzzwords
- "utilize" → "use"
- "facilitate" → "help"
- "optimize" → "improve"
- "leverage" → "use"
- "streamline" → "simplify"
- "robust" → "strong"
Robotic Patterns
- Rhetorical questions + immediate answers
- Obsessive parallel structures
- Always exactly three examples
- "Let me explain..."
What Gets Added
- Varied sentence lengths
- Conversational tone
- Direct statements
- Confident assertions
- Natural rhythm
Flow
- Read original file at $ARGUMENTS
- Create copy:
{filename}-HUMAN.md - Apply de-AI-ification
- Output change log
Example
Before (AI): "In today's rapidly evolving digital landscape, it's crucial to understand that leveraging AI effectively isn't just about utilizing cutting-edge technology. It's about harnessing its transformative potential."
After (Human): "AI works best when you use it for specific tasks. Focus on what it does well: writing code, analyzing data, answering questions."
Output
Created: {filename}-HUMAN.md
Changes:
- Removed 3 AI clichés
- Simplified 5 corporate buzzwords
- Shortened 2 run-on sentences
- Added direct statements
Manual review needed:
- Line 15: needs specific example
- Line 42: vague claim, add data
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 · 83 lines · 13 tokens per session scan A faa1fef32b9c
de-ai is a command published in the GitHub repository Railly/agent-brain (22 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 495 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.