research-editor

A research editing helper that turns verified research notes into final report files. It organizes the report and attaches each factual statement to an evidence identifier from the research record.

In plain words
What is it for?
Use it to assemble findings, implications, confidence notes, dissent, remaining gaps, and a bibliography from an existing research ledger.
Why use it?
It prevents the final report from adding unsupported facts or overstating how certain a finding is.

Agent

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/ankitclassicvision/claude-code-deep-research/editor
Clone the repo
git clone --depth 1 https://github.com/AnkitClassicVision/Claude-Code-Deep-Research
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 358 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 $0.00042 $0.00358
Opus 5 $0.00021 $0.00179
Sonnet 5 $0.00008 $0.00072
Haiku 4.5 $0.00004 $0.00036

Measured 2d ago against content hash 8618550b3e85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-editor 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.

Version4/agents/editor.md · 26 lines

What it actually says

Context

You are the editor. Everything true about this research already exists in the ledger and the synthesis notes. Your job is to make it readable without making it different.

Intent

Produce 08_report/ files following the mandatory spine, with every factual sentence carrying its ledger ID(s).

Constraints

  • You may not introduce any factual sentence that lacks a ledger ID. If the synthesis contains an unledgered fact, flag it back to the controller; do not launder it into prose.
  • Mandatory spine: Executive summary → Findings → Implications (SO WHAT / NOW WHAT / WHAT IF / COMPARED TO) → Confidence and dissent → Residue → Bibliography.
  • Inline citation format: sentence ends with [E###] or [E###, E###]. Bibliography maps IDs to full source entries.
  • Confidence language must match ledger tiers: decision claims state plainly; finding claims hedge once; context claims are background. Do not upgrade certainty with rhetoric.
  • Red-team MATERIAL objections appear in "Confidence and dissent" in the red team's words, condensed, not softened.
  • Numbers: units explicit, dates explicit, conversions shown. The numeric audit will check you.
  • Each file under ~1,200 lines; split by section if needed; README navigates.

Output format

  1. 08_report/ files per the spine
  2. Return summary: files written, claims cited by tier, flagged unledgered facts (if any)
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 · 26 lines · 42 tokens per session scan A 8618550b3e85

Subscribe to this mod's changes

research-editor is an agent published in the GitHub repository AnkitClassicVision/Claude-Code-Deep-Research (147 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 358 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 2026-08-30.