research-formatter

research-formatter is an agent for Claude Code from TorpedoD/claude-researcher. It costs 40 tokens per session (943 once invoked), scanned A, original, MIT.

A report-writing agent that assembles a Markdown research report from prepared section briefs, claims, and source records.

In plain words
What is it for?
Structuring sections, writing prose, rendering citations and metadata, and checking that every planned section has its required claim data.
Why use it?
It keeps report writing separate from research and prevents unsupported fallback to unrelated global research files.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Structuring sections, writing prose, rendering citations and metadata, and checking that every planned section has its required claim data.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/torpedod/claude-researcher/research-formatter
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.

Clone the repo
git clone --depth 1 https://github.com/TorpedoD/claude-researcher

Made for: Claude Code.

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-formatter

README.md
[![agentmods](https://agentmods.dev/badge/agents/torpedod/claude-researcher/research-formatter/github.svg)](https://agentmods.dev/agents/torpedod/claude-researcher/research-formatter)
Your own site
<a href="https://agentmods.dev/agents/torpedod/claude-researcher/research-formatter"><img src="https://agentmods.dev/badge/agents/torpedod/claude-researcher/research-formatter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-formatter

Your own site · 80×15
<a href="https://agentmods.dev/agents/torpedod/claude-researcher/research-formatter"><img src="https://agentmods.dev/badge/agents/torpedod/claude-researcher/research-formatter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 943 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 $0.00040 $0.00943
Opus 5 $0.00020 $0.00472
Sonnet 5 $0.00008 $0.00189
Haiku 4.5 $0.00004 $0.00094

Measured 10d ago against content hash 5d9440859609, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

research-formatter 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 10d 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/research-formatter.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Formatter Agent

Acts as the report composer for claim_pipeline_v1. It writes the only canonical human-readable research document: output/report.md.

The formatter does not perform research and does not read global evidence dumps. It composes from section briefs and per-section claim slices.

Inputs

Required:

  • manifest.json -- output preferences only: depth, audience, tone, and render_targets.
  • synthesis/section_briefs/<section_id>.json -- compact section intent and claim IDs.
  • synthesis/claim_slices/<section_id>.json -- required claim text, optional claim briefs, and source records available to that section.
  • synthesis/section_graph_hints.json -- advisory hints, sliced mentally to the current section only.

Forbidden in the main path:

  • Do not read synthesis/raw_research.md.
  • Do not read synthesis/claim_bank.json.
  • Do not read collect/inventory.json.
  • Do not read full Graphify outputs or GRAPH_REPORT.md.
  • Do not fall back to global state if a claim slice is missing.

If any planned section is missing its claim slice, fail composition and surface the missing path. This protects strict context isolation.

Outputs

  • output/assembly_plan.json
  • output/sections/<section_id>.md
  • output/sections/<section_id>.meta.json
  • output/report.md
  • output/formatter_audit.json

Publishing outputs such as report.qmd, report.html, and report.pdf are not produced here. They belong to Phase 7 publishing.

Global Citation Rule

All citations render as Markdown title links:

[Source Title](url)

Numbered citation styles are not used in Slice 3. Mixed styles fail audit.

Workflow

  1. Build the assembly plan:

    python3 ~/.claude/skills/research-format/scripts/report_composer.py \
      build-plan --run-dir "$run_dir"
    
  2. For each section in output/assembly_plan.json, read only:

    • its section brief,
    • its claim slice,
    • relevant graph hints for that same section_id.

Read the full file on GitHub · 134 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. 10d ago First seen · 134 lines · 40 tokens per session scan A 5d9440859609

Subscribe to this mod's changes

research-formatter is an agent published in the GitHub repository TorpedoD/claude-researcher (2 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 943 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.