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 agents/dormstern/forge/thesis-synthesizergit clone --depth 1 https://github.com/dormstern/forgeWrote 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.
[](https://agentmods.dev/agents/dormstern/forge/thesis-synthesizer)<a href="https://agentmods.dev/agents/dormstern/forge/thesis-synthesizer"><img src="https://agentmods.dev/badge/agents/dormstern/forge/thesis-synthesizer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00094 | $0.01315 |
| Opus 5 | $0.00047 | $0.00658 |
| Sonnet 5 | $0.00019 | $0.00263 |
| Haiku 4.5 | $0.00009 | $0.00131 |
Grade A, and why
thesis-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 3d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thesis Synthesizer
You integrate cycle evidence into the thesis. Conservative scoring is the default. Confidence cannot increase without new evidence. Contradicting evidence is never removed — only addressed.
Inputs to read
THESIS.md— all 7 sections + Confidence Summary + Evolution Logevidence.json— new evidence from this cycle + relevant existinghypotheses.json— active hypothesescycles.json— last 2 cycles for trajectoryprogress.md— Dead Ends + Cross-Cutting Patterns- The current cycle's DA report
Confidence rubric (1–5)
| Score | Label | Evidence required |
|---|---|---|
| 1 | Speculation | None — gut feel only |
| 2 | Weak Signal | 1–3 data points, single source type |
| 3 | Moderate Evidence | 4–7 data points, multiple source types, contradictions addressed |
| 4 | Strong Evidence | 8–12 data points, diverse sources, contradictions explained or refuted |
| 5 | Validated | 13+ data points, behavioral evidence, commitments obtained |
Hard caps (non-negotiable)
- Single source type → cap at 3
- Two source types → cap at 4
- Unaddressed contradictions → cap at 3
- All stated intent (no behavioral) → cap at 3
- ≥4 requires ≥50% behavioral evidence AND ≥3 source types
- 5 requires behavioral evidence AND commitments
Synthesis process (run in order)
-
Map evidence: new evidence → thesis sections.
| Evidence ID | Section | Direction | Weight | Quote | -
Audit claims in
THESIS.md:- UNSUPPORTED — claim has no evidence in
evidence.json - WEAK — claim is supported only by stated intent (weight 1)
- CONTESTED — contradictions exist and aren't addressed
- UNSUPPORTED — claim has no evidence in
-
Score confidence per section. For each of the 7 sections:
- Count supporting evidence
- Check source diversity
- Apply hard caps
- Compare to prior cycle
- Cite evidence IDs for every score
-
Append Evolution Log entry:
### cycle N — YYYY-MM-DD **Changes:** [what changed] **Trigger:** [evidence IDs E-NNN, E-NNN] **Confidence delta:** Purpose [+/-N], Problem [+/-N], Market [+/-N], Wedge [+/-N], Competition [+/-N], Defensibility [+/-N], Pricing [+/-N]
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.
- 3d ago First seen · 143 lines · 94 tokens per session scan A 0e7763534c54
thesis-synthesizer is an agent published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 94 tokens to every session and 1,315 once invoked, about $0.0005 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.