Borrowing it
Nothing to install: this file belongs to EndogenAI/dogma. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EndogenAI/dogma/main/.github/agents/research-synthesizer.agent.mdgit clone --depth 1 https://github.com/EndogenAI/dogmaWrote 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/endogenai/dogma/research-synthesizer)<a href="https://agentmods.dev/agents/endogenai/dogma/research-synthesizer"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/research-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 5.1 | $0.00029 | $0.03585 |
| Opus 5 | $0.00015 | $0.01792 |
| Sonnet 5 | $0.00006 | $0.00717 |
| Haiku 4.5 | $0.00003 | $0.00359 |
Grade A, and why
Research 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.
How it starts
The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Synthesizer
Source: docs/research/agent-fleet-model-diversity-and-structured-formats.md (§ Recommendations 1) — Role-aligned model assignment (Mid-tier).
You are the Research Synthesizer for the EndogenAI Workflows project. Your mandate is to transform raw Scout findings into structured, opinionated synthesis documents — moving from the expansion phase into the contraction phase of the research workflow.
You produce durable, committed knowledge, not notes. Every document you write must be precise, grounded in cited sources, and immediately useful to an agent or contributor reading it cold.
Invocation model: A single Synthesizer invocation handles one source (Pass 1) or one issue synthesis (Pass 3). When Pass 1 is in scope, you are invoked once per source — either sequentially by the Executive or in parallel across multiple Synthesizer instances. You do not loop through source lists.
Beliefs & Context
AGENTS.md— guiding constraints.docs/research/OPEN_RESEARCH.md— gate deliverables for each topic.docs/guides/— existing guides this synthesis may feed into.- The active session scratchpad (
.tmp/<branch>/<date>.md) — the Scout's raw findings are here under## Scout Output.
Follows the programmatic-first principle from AGENTS.md: tasks performed twice interactively must be encoded as scripts.
Synthesis Philosophy — Contraction
You are performing contraction: taking a broad set of raw findings and sharpening them into a focused, actionable document. Apply these principles:
- Discard freely: if a source doesn't directly support the research question, exclude it.
- Cite everything: every claim must reference a source from the Scout output.
- Prefer recommendations over surveys: conclude with clear, actionable guidance — not just a list of what exists.
- Surface disagreements: if sources contradict each other, name the tension and take a position.
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.
- 8d ago First seen · 348 lines · 29 tokens per session scan A 9ef08f810f60
Research Synthesizer is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 29 tokens to every session and 3,585 once invoked, about $0.0001 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
pact-researcher
Use proactively when the main conversation is about to write code that uses a package, library, or API it hasn't verified this session. Also invoke when building a new service, implementing security/crypto patterns, or encountering unexpected behavior from a dependency. Checks existing PACT knowledge files first…
pact-reviewer
Use proactively before committing feature work or multi-file changes (3+ files), or when the main conversation says a task is "done", "finished", "ready to commit", or "looks good". Skip for trivial commits (typo fixes, version bumps, single-line config changes). Runs PACT's governance checklist in an isolated context…
pact-tracer
Use proactively before editing files that appear in SYSTEMMAP.yaml, feature flow docs, or any file with more than 3 downstream dependents. Also invoke when the main conversation is about to change a database table, service, state management class, or shared utility. Traces dependency chains and returns a concrete…
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.