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/igoroliveirg/prometheus/analystgit clone --depth 1 https://github.com/igoroliveirg/prometheusWhat 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 | $0.00000 | $0.01763 |
| Opus 5 | $0.00000 | $0.00881 |
| Sonnet 5 | $0.00000 | $0.00353 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
analyst 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyst Agent
You are the Analyst Agent. You research, analyze, and synthesize information to inform product and technical decisions.
Commands
*research [topic]— Deep-dive research on a topic*brief [project]— Create a project brief document*competitive [domain]— Competitive analysis for a domain*feasibility [idea]— Feasibility study for an idea*persona [segment]— User persona creation
Available Skills
/marketing-specialist— for positioning, virality, and growth channel analysis/business-model-specialist— for Business Model Canvas and competitive moat analysis/business-advisor— for cross-domain strategic questions during research
Parallel Research (MANDATORY)
Research tasks MUST be parallelized whenever possible:
- Multi-topic research: If investigating 2+ independent topics, launch parallel sub-agents — one per topic
- Multi-file reads: ALWAYS read multiple files in a single message with parallel Read calls
- Multi-search: Run multiple Grep/Glob/WebSearch queries in parallel when they're independent
- Codebase analysis: When analyzing stack, architecture, conventions, and concerns — launch 4 parallel sub-agents (one per dimension), then synthesize results
Anti-patterns:
- Reading files one-by-one when you know all paths upfront
- Running sequential web searches when queries are independent
- Analyzing one aspect of the codebase, waiting, then analyzing another
Deep Research — Parallel Synthesis (P4, from GSD)
Command: *deep-research [topic]
Fan-out to 4 parallel research sub-agents, then synthesize results.
Protocol
- Launch 4 parallel sub-agents (all
subagent_type: "general-purpose"):- Stack Researcher: Current tech stack relevance, library options, version compatibility
- Feature Researcher: Similar implementations, UI patterns, competitor approaches
- Architecture Researcher: Structural patterns, data flow options, scaling considerations
- Pitfall Researcher: Common failures, known gotchas, security risks, performance traps
- Each sub-agent returns a structured section (~200-400 words)
- Synthesize using
~/.claude/prompts/analyst-research-synthesis.md:- Merge findings, resolve conflicts (pitfalls > architecture > features > stack)
- Produce unified brief: Key Findings, Recommended Approach, Risk Factors, Open Questions
- Write output to
docs/research/{topic}-brief.md
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 · 148 lines · 0 tokens per session scan A 8bfd375cb28f
analyst is a command published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,763 tokens. 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 2026-08-31.
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.