synthesize

A command for combining the evidence gathered during one research cycle into the product thesis, which is the written statement of what the product is based on and why it may work.

In plain words
What is it for?
Use it after a Founder-mode research cycle to update the thesis, record what changed, score each section, and identify the biggest evidence gaps.
Why use it?
It identifies unsupported or disputed claims and applies consistent confidence scores instead of treating every signal as proof.

Command

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 commands/dormstern/forge/synthesize
Clone the repo
git clone --depth 1 https://github.com/dormstern/forge
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 531 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 $0.00036 $0.00531
Opus 5 $0.00018 $0.00266
Sonnet 5 $0.00007 $0.00106
Haiku 4.5 $0.00004 $0.00053

Measured 2d ago against content hash 0c2929b2024e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synthesize 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.

commands/synthesize.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge:synthesize — Thesis synthesis (Founder mode)

Execution mode: direct. This command has explicit steps below — execute them in order. Do not enter plan mode, do not write a plan file, do not call ExitPlanMode. The framework already did the planning; you just run the steps.

You dispatch the thesis-synthesizer agent to update THESIS.md based on the cycle's evidence and DA report.

Behavior

  1. Read THESIS.md (all 7 sections + current confidence), evidence.json (new evidence from this cycle), interviews.md (latest summaries), cycles.json (last 2 cycles for trajectory), and the latest DA report.

  2. Dispatch thesis-synthesizer to:

    • Map new evidence to thesis sections (with evidence IDs)
    • Audit claims (UNSUPPORTED / WEAK / CONTESTED)
    • Score confidence per section using the 1–5 rubric with hard caps:
      • Single source type → cap 3
      • Two source types → cap 4
      • Unaddressed contradictions → cap 3
      • All stated intent (no behavioral) → cap 3
      • ≥4 requires ≥50% behavioral evidence AND ≥3 source types
      • 5 requires behavioral evidence AND commitments
    • Append an Evolution Log entry (changes, trigger evidence, confidence delta)
    • Identify the weakest section and propose specific next-cycle tests
  3. Update THESIS.md with new scores. Update cycles.json with this cycle's confidence_snapshot and confidence_delta.

  4. PAUSE — Present the synthesis report. The user reviews and accepts or challenges the scores. Conservative scoring is the default; argue up only if the user provides specific evidence.

Constraints

  • Confidence cannot increase without new evidence.
  • Contradicting evidence is never removed — only addressed.
  • Stagnation across 2+ cycles → flag for methodology review.
  • Trajectory down 2+ cycles → consider PIVOT or KILL recommendation.

Reference

Read the full file on GitHub · 44 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. 2d ago First seen · 44 lines · 36 tokens per session scan A 0c2929b2024e

Subscribe to this mod's changes

synthesize is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 531 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 2026-08-31.