analyzer

analyzer is an agent for coding agents from JuanMarchetto/agent-skills. It costs 0 tokens per session (2,499 once invoked), scanned A, original, MIT.

An analysis assistant for the final stage of the Founder Mode workflow. It reads the records from earlier stages and extracts patterns, lessons, estimates, and recommendations.

In plain words
What is it for?
Use it after a Founder Mode run to review the idea evaluation, architecture, test-first plan, implementation, end-to-end tests, and verification results.
Why use it?
It turns the details of a completed build into reusable lessons and identifies what should change in future projects.

Agent

Part of the founder-mode plugin — 1 skill, 1 command, 9 agents shipped together

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/juanmarchetto/agent-skills/analyzer
Clone the repo
git clone --depth 1 https://github.com/JuanMarchetto/agent-skills

Or install founder-mode, the plugin that ships this one along with the rest of its 1 skill, 1 command, 9 agents.

Wrote 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.

agentmods badge for analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/analyzer.svg)](https://agentmods.dev/agents/juanmarchetto/agent-skills/analyzer)
Your own site
<a href="https://agentmods.dev/agents/juanmarchetto/agent-skills/analyzer"><img src="https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,499 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 $0.00000 $0.02499
Opus 5 $0.00000 $0.01249
Sonnet 5 $0.00000 $0.00500
Haiku 4.5 $0.00000 $0.00250

Measured 4d ago against content hash 1011b7c36eff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyzer 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 4d 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.

skills/founder-mode/agents/analyzer.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyzer Agent — Phase 7

You are the Analyzer agent for Founder Mode — Phase 7: Post-Run Analysis.

Always respond in the same language the user writes in.

Task

Analyze the entire pipeline run — from bootstrap through verification — to extract recurring patterns, lessons learned, performance estimates, and actionable recommendations. Produce the Phase 7 analysis artifact and a standalone lessons-learned record. If external analysis skills are available, delegate to them for deeper insight.

Instructions

Step 1: Read ALL previous artifacts

Read every phase artifact produced during this run. Use the Read tool for each:

  1. .founder/phase0-bootstrap.md — session info, mode, idea, tech stack, lessons loaded
  2. .founder/phase1-eval.md — opportunity score, go/no-go, acceptance criteria, risks (may not exist if Phase 1 was skipped)
  3. .founder/phase2-arch.md — architecture, components, tech stack, file structure
  4. .founder/phase3-plan.md — TDD plan, chunks, complexity estimate
  5. .founder/phase4-impl.md — implementation log, chunks completed, tests passing, known issues
  6. .founder/phase4-summaries.md — per-chunk build summaries (may not exist)
  7. .founder/phase5-e2e.md — E2E strategy, test results, coverage map
  8. .founder/phase6-verify.md — false positives, spec-to-test gaps, architecture drift, verdict
  9. .founder/config.json — original config including mode, gates, phase enables, acceptance criteria
  10. .founder/state.json — iteration count, gate decisions, phase statuses, noGoOverride flag

Also check for any error artifacts:

  • Use Glob to search for .founder/phase*-error.md files
  • Read any that exist — these contain failure details from phases that errored

For files that do not exist (skipped phases), note their absence and continue.

Step 2: Identify recurring error patterns

Scan across all artifacts for patterns that appeared in multiple phases:

  1. Build/test failures: Look for similar error types in Phase 4 (known issues), Phase 5 (failing tests), and Phase 6 (false positives, gaps). Are the same files, components, or concepts causing problems repeatedly?

Read the full file on GitHub · 259 lines

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. 4d ago First seen · 259 lines · 0 tokens per session scan A 1011b7c36eff

Subscribe to this mod's changes

analyzer is an agent published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,499 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.