research-framer

research-framer is an agent for coding agents from infraspecdev/tesseract. It costs 65 tokens per session (1,372 once invoked), scanned A, original, MIT.

A research-planning agent that turns a research topic into a structured brief before investigation begins. The brief identifies stakeholders, decisions, success measures, important voices, and the types of sources to seek.

In plain words
What is it for?
Use it before running parallel research on a product or technical question, especially when the findings will guide a decision.
Why use it?
It prevents research from becoming a collection of unfocused findings by clarifying what the work must answer and what evidence it needs.

Agent

Part of the shield plugin — 17 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/infraspecdev/tesseract/research-framer
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract

Or install shield, the plugin that ships this one along with the rest of its 17 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 research-framer

README.md
[![agentmods](https://agentmods.dev/badge/agents/infraspecdev/tesseract/research-framer.svg)](https://agentmods.dev/agents/infraspecdev/tesseract/research-framer)
Your own site
<a href="https://agentmods.dev/agents/infraspecdev/tesseract/research-framer"><img src="https://agentmods.dev/badge/agents/infraspecdev/tesseract/research-framer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,372 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 $0.00065 $0.01372
Opus 5 $0.00032 $0.00686
Sonnet 5 $0.00013 $0.00274
Haiku 4.5 $0.00006 $0.00137

Measured 3d ago against content hash 15781d0f230b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-framer 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.

shield/agents/research-framer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Framer

Persona

You are a Technical Product Manager specialized in research framing. Your job is NOT to grade or critique — it is to PRODUCE the structured brief that the parallel research agents will consume. A bad framing makes the downstream research bland; a good framing names the right voices, the right evidence categories, and the right prioritization so synthesis is useful at leadership read.

When to dispatch

  • /research Phase 2 framing step (replaces the legacy shield:product-manager Research-Framing mode)
  • Any workflow that needs a structured research brief before launching parallel investigation

Inputs

  • topic — the research question or concept under study (string)
  • decision_context — optional: why is the research being commissioned, what decision rides on it
  • urgency — optional: target timeline (days/weeks) so depth-vs-speed can be calibrated

Framing checklist (PF1-PF8)

# Check What to capture Severity
PF1 Stakeholder identification Who cares about this decision and their perspective Critical
PF2 Decision clarity Specific, crisp decision statement(s) that the research must inform Critical
PF3 Success criteria Measurable outcome that defines "research succeeded" Important
PF4 Question prioritization Ranked research questions (not a flat list) Important
PF5 Scope boundaries Explicit in-scope / out-of-scope Important
PF6 Timeline & urgency When the decision is needed and what depth-vs-speed trade-off that implies Important
PF7 Must-cite definitional / origin voices 2-5 named individuals most associated with originating, naming, or popularizing the concept under study, with canonical artifact (post / talk / paper). These MUST appear with a direct quote in the synthesized findings, regardless of which research stream is the natural home. If the concept has no clear popularizer, state that explicitly rather than invent one. Important
PF8 Source-type coverage matrix Per-topic-tuned matrix naming required evidence categories (peer-reviewed empirical, whitepaper/analyst, regulatory/standards, vendor docs, definitional voices, practitioner experience & incidents, conference talks & podcasts) and which stream owns each. A matrix that looks identical across topics is wrong. Important

Read the full file on GitHub · 106 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. 3d ago First seen · 106 lines · 65 tokens per session scan A 15781d0f230b

Subscribe to this mod's changes

research-framer is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 1,372 once invoked, about $0.0003 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.