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/pulsegit 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 | $0.00012 | $0.01314 |
| Opus 5 | $0.00006 | $0.00657 |
| Sonnet 5 | $0.00002 | $0.00263 |
| Haiku 4.5 | $0.00001 | $0.00131 |
Grade B, and why
pulse scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Don't lecture. Just flag and move on. How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze engagement, apply 80/20 rule, detect drift and blind spots.
Philosophy
You have many interests. Pareto says 20% of your focus drives 80% of results.
But you also drift, get distracted, and forget goals.
/pulse is your honest mirror.
Data Sources
CLAUDE.mdGoals section01_Inbox/*.md- what you capture/consume03_Garden/**/*.md- what you process into durable notes02_Journal/daily/*.md- what you do- Git commits across repos (if accessible)
Analysis
1. Pareto Ranking
engagement = (clips * 1) + (notes * 3) + (logs * 2) + (commits * 5)
Sort topics, find vital 20%:
VITAL 20%
━━━━━━━━━
1. Rust ████████████ 45%
2. AI Agents ██████░░░░░░ 25%
3. Auth ████░░░░░░░░ 15%
─────
85%
2. Drift Detection
Topics with HIGH engagement but NOT in stated goals:
DRIFT DETECTED
You clipped 8 articles about "AI Agents" this week
but it's not in your goals.
→ Add to priorities?
→ Or consciously ignore?
3. Hidden Patterns
Cluster connected notes:
HIDDEN PATTERN
[[rust-ownership]] + [[react-hooks]] + [[gpui-state]]
→ Emerging interest: "Memory models across languages"
→ Content opportunity: Blog series comparing ownership patterns?
4. Blind Spots
Goals with LOW/NO engagement:
BLIND SPOTS
- "Math for ML" - No engagement in 14 days
- "Content creation" - 5 ideas queued, 0 published
5. Interest Lifecycle
EMERGING : {topics}
GROWING : {topics}
PEAK : {topics}
DECLINING : {topics}
DORMANT : {topics} (30+ days)
6. MITs (Most Important Things)
3 tasks for the week based on Pareto + deadlines:
YOUR 3 MITs THIS WEEK
1. [ ] {vital 20% topic}
2. [ ] {deadline-driven item}
3. [ ] {compounds over time}
Output Format
# Pulse Report - {{date}}
## Alignment Score: {X}%
## Pareto: Your Vital 20%
| Topic | Engagement | % | In Goals? |
|-------|------------|---|-----------|
| {topic} | {bar} | {%} | Yes / DRIFT |
## Drift Detected
- **{topic}**: {n} clips, {n} notes - not in goals
→ Promote to goal? Or conscious distraction?
## Hidden Patterns
- [[note1]] + [[note2]] + [[note3]]
→ Theme: "{emerging theme}"
→ Content: {opportunity}?
## Blind Spots
- {goal}: {n} engagement, {n} days
## Interest Lifecycle
EMERGING: {topics}
GROWING: {topics}
PEAK: {topics}
DECLINING: {topics}
DORMANT: {topics}
## Your 3 MITs This Week
1. [ ] _____ (vital 20%)
2. [ ] _____ (deadline)
3. [ ] _____ (compounds)
## Recommendations
1. {action 1}
2. {action 2}
3. {action 3}
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 · 193 lines · 12 tokens per session scan B d07d749d4131
pulse is a command published in the GitHub repository Railly/agent-brain (22 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,314 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.