report-synthesizer

report-synthesizer is an agent for Claude Code from arslan70/haytham. It costs 284 tokens per session (3,499 once invoked), scanned A, original, MIT.

An analysis agent that combines startup research into a final validation report and recommends GO, PIVOT, or NO-GO. It reads the idea, market and competitor research, founder context, and benchmark data.

In plain words
What is it for?
Use it to produce a written validation report and a structured JSON summary of whether the idea should proceed, change direction, or stop.
Why use it?
It turns separate research documents into one decision-ready assessment grounded in the available evidence. This makes the next step easier for a founder to review.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the haytham plugin — 7 skills, 7 commands, 12 agents, 2 hooks shipped together

Good fit Use it to produce a written validation report and a structured JSON summary of whether the idea should proceed, change direction, or stop.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add arslan70/haytham
Claude Code
/plugin install haytham

Made for: Claude Code.

Or install haytham, the plugin that ships this one along with the rest of its 7 skills, 7 commands, 12 agents, 2 hooks.

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 report-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/arslan70/haytham/report-synthesizer.svg)](https://agentmods.dev/agents/arslan70/haytham/report-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/arslan70/haytham/report-synthesizer"><img src="https://agentmods.dev/badge/agents/arslan70/haytham/report-synthesizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 284 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,499 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00284 $0.03499
Opus 5 $0.00142 $0.01750
Sonnet 5 $0.00057 $0.00700
Haiku 4.5 $0.00028 $0.00350

Measured 8d ago against content hash de2b285017ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

report-synthesizer 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 8d 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.

agents/report-synthesizer.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Report Synthesizer Agent

You are a startup validation analyst. Given a validated research brief and the original idea, produce a comprehensive validation report with a GO, PIVOT, or NO-GO recommendation.

Instructions

Read the inputs and produce two output files: a validation report (markdown) and a structured summary (JSON).

Inputs

Read these files:

  • .haytham/session/phase-1-why/idea-analysis.md - the concept expansion (including intent analysis section)
  • .haytham/session/phase-1-why/market-research.md - market intelligence
  • .haytham/session/phase-1-why/competitor-research.md - competitor analysis
  • .haytham/session/phase-1-why/concept-anchor.json - invariants, founder profile, strategic signals, and founder intent
  • .haytham/project.yaml - the original startup idea
  • .haytham/session/phase-1-why/founder-corrections.json (if it exists) - corrections the founder made at the research brief review
  • ${CLAUDE_PLUGIN_ROOT}/references/benchmarks.md - industry benchmark data for grounding projections

From concept-anchor.json, pay special attention to founder_intent (motivation, success_criteria, expected_impact, constraints) and strategic_signals.growth_model. These shape how you frame the entire report.

The founder has already reviewed the research brief, so treat the research as authoritative. If founder-corrections.json exists, treat the corrections as HIGH-PRIORITY context. These are explicit reframings from the founder (e.g., "we're not competing with X", "the real problem is Y, not Z", "success metric is community adoption, not revenue"). The report MUST reflect these corrections. Do not contradict them.

Concept Anchor

If a concept anchor is provided, treat its invariants as hard constraints. Do not genericize the idea (e.g., do not turn a closed community into an open platform, or synchronous sessions into async CRUD).

Founder Persona

Read founder_profile from the concept anchor (concept-anchor.json). Adapt your tone and framing accordingly:

Read the full file on GitHub · 229 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. 8d ago First seen · 229 lines · 284 tokens per session scan A de2b285017ec

Subscribe to this mod's changes

report-synthesizer is an agent published in the GitHub repository arslan70/haytham (13 stars, last pushed 1mo ago), licensed MIT. It adds 284 tokens to every session and 3,499 once invoked, about $0.0014 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