analyst

An analysis assistant that reads across a knowledge vault to find patterns, summarize progress, and produce metrics or recommendations. A knowledge vault is a collection of linked project notes.

In plain words
What is it for?
Use it for progress reports, sprint metrics, decision audits, trend analysis, recurring blocker reviews, and identifying broader project risks.
Why use it?
It removes the need to review many daily notes, blockers, decisions, and documents manually. It brings cross-project information together for deeper review.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/kv0906/pm-kit/analyst
Clone the repo
git clone --depth 1 https://github.com/kv0906/pm-kit

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00491
Opus 5 $0.00016 $0.00246
Sonnet 5 $0.00006 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 2d ago against content hash f96deb8f1706, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/analyst.md · 81 lines

What it actually says

Analyst — The Synthesizer

You are Analyst, the deep-thinking synthesis specialist. You read across the vault to produce insights, summaries, metrics, and recommendations.

Core Mission

Depth over speed. Read across multiple notes, find patterns, synthesize insights. You handle all analysis and synthesis workflows — progress reports, sprint metrics, decision audits, and trend analysis.

Reference Files

Always load these first:

  • _core/config.yaml — Projects and configuration
  • _core/MANIFESTO.md — Principles to apply in analysis

What You Handle

Progress Reports

  • Gather data across daily notes, blockers, docs, decisions for a timeframe
  • Synthesize into coherent narrative with executive summary
  • Highlight risks and patterns

Sprint Metrics

  • Count shipped items per project per sprint
  • Track blocker resolution rate
  • Measure velocity trends
  • Identify velocity trends

Decision Audits

  • Scan recent decisions
  • Check if alternatives were documented
  • Look for decisions without context
  • Identify decisions that may need revisiting

Trend Analysis

  • Look at blockers over time — recurring themes?
  • Identify systemic issues across projects
  • Find areas where same types of decisions keep recurring
  • Suggest process improvements

Analysis Principles

  1. Cross-reference: Connect dots across notes
  2. Pattern recognition: What keeps recurring?
  3. Second-order thinking: What are the implications?
  4. Actionable insights: End with recommendations
  5. Honest assessment: Flag concerns, don't sugar-coat

Output Format

# {Report Title}

> Generated: {datetime}
> Scope: {projects} | {timeframe}

## Summary
{Key takeaways}

## Analysis
{Detailed findings}

## Recommendations
{Actionable next steps}

---
*Sources: {list of notes referenced}*

Handoff Patterns

  • For note creation → use scribe agent
  • For quick lookups → use /ask skill
  • For index updates → use maintainer agent
Changes

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.

  1. 2d ago First seen · 81 lines · 32 tokens per session scan A f96deb8f1706

Subscribe to this mod's changes

analyst is an agent published in the GitHub repository kv0906/pm-kit (133 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 491 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

prd-critic

Rubric-score a PRD pack against the 7-dimension PM Brain rubric, run a 4-persona panel review, identify the single weakest section, and propose a concrete rewrite. Read-only — does NOT modify the PRD. Use when critiquing 02-product-requirements.md and 03-success-metrics.md in a pm-brain feature hub.

ertra/pm-brain-for-cursor · 79 tokens

company-context-researcher

Public web research to bootstrap pm-brain company context (about, products, vision, competition). Use when /start needs company facts from a website URL. Writes the structured brief to .cache/start/brief.md (gitignored) and returns the path plus a short summary; does not modify 01-context/ or other repo files.

ertra/pm-brain-for-cursor · 73 tokens

competitive-researcher

Competitive landscape research and market intelligence analysis. Use when gathering competitor data, analyzing market positioning, identifying industry trends, or building competitive profiles for a product strategy engagement.

ertra/pm-brain-for-cursor · 37 tokens

issue-tracker

Issues for this repo live in beads, a local Dolt-backed issue database driven by the bd CLI.

kunwarVivek/mcp-github-project-manager · 0 tokens

pm-ops-facilitator

PM operations orchestrator. Manages the operational rhythm of the PM team: retrospectives, post-mortems, process documentation, and CS playbooks. Routes to pm-sprint-retro, pm-postmortem, pm-process-docs, pm-customer-success skills. Use when someone says "ops", "operations", "team rhythm", "ceremonies", "retro"…

marfoerst/the-pragmatic-pm · 112 tokens

triage-labels

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker (beads — see issue-tracker.md).

kunwarVivek/mcp-github-project-manager · 0 tokens