research_report

research_report is a command for Claude Code from arnaudgelas/K-Ops. It costs 2 tokens per session (536 once invoked), scanned A, original, MIT.

A command for drafting a final research report from a brief, collected findings, source notes, and a critical review.

In plain words
What is it for?
It helps write the report's summary, method, evidence analysis, and engineering recommendations in the repository's Markdown format.
Why use it?
It turns scattered research materials into one bounded report while requiring important claims to point back to source notes.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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 commands/arnaudgelas/k-ops/research_report
Clone the repo
git clone --depth 1 https://github.com/arnaudgelas/K-Ops

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_report

README.md
[![agentmods](https://agentmods.dev/badge/commands/arnaudgelas/k-ops/research_report.svg)](https://agentmods.dev/commands/arnaudgelas/k-ops/research_report)
Your own site
<a href="https://agentmods.dev/commands/arnaudgelas/k-ops/research_report"><img src="https://agentmods.dev/badge/commands/arnaudgelas/k-ops/research_report.svg" alt="Measured on agentmods" height="20"></a>
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 5.1 $0.00002 $0.00536
Opus 5 $0.00001 $0.00268
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00054

Measured 5d ago against content hash 6542a23a25ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

research_report 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 5d 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.

.claude/commands/research_report.md · 37 lines

What it actually says

You are the Research Report agent for this repository.

Goal:

  • Draft the final research report synthesizing the brief, findings, and contrarian review into a bounded, evidence-grounded deliverable.

Inputs:

  • Research brief: research/briefs/-.md
  • Findings file: research/findings/-.md
  • Review file: research/notes/-contrarian-review.md
  • Report file: research/reports/-.md

Instructions:

  1. Synthesize inputs: Read the brief, findings, source notes, and contrarian review thoroughly.
  2. Draft the report:
    • Write/update research/reports/<topic-slug>-<date>.md. Preserve its frontmatter (type: research-report, topic_slug, etc.).
    • Under ## Executive Summary, provide a high-level overview of the findings, conclusions, and engineering recommendations.
    • Under ## Methodology, briefly detail the source collection and review process.
    • Under ## Evidence and Analysis, write the core sections. Every key fact or claim must be directly cited with Obsidian wikilinks to the source summaries (e.g. [[Sources/src-<id>|src-<id>]]). Group findings logically.
    • Under ## Engineering Recommendations, list concrete actionable steps derived from the evidence.
    • Under ## Contradictory or Missing Evidence, explicitly address each objection and gap raised in the contrarian review and document remaining uncertainties or contradictions between sources.
    • Under ## Source Map, list all concept pages and source summaries (with Obsidian wikilinks) that informed this report.
  3. Evidence bounds:
    • Keep conclusions strictly bounded by the collected evidence. Avoid making general or sweeping assertions that aren't backed by the cited sources.
    • If a claim relies on an imported model report, ensure it has been verified against a primary source before including it in the report.
  4. Progress Log: Append a short progress update when done.

Done checklist:

  • Completed report saved in research/reports/<topic-slug>-<date>.md with all required sections (Executive Summary, Methodology, Evidence and Analysis, Engineering Recommendations, Contradictory or Missing Evidence, Source Map) populated.
  • All claims are backed by source citations.
  • Objections from the contrarian review are addressed or documented as open questions.
  • No placeholders remain in the report.
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. 5d ago First seen · 37 lines · 2 tokens per session scan A 6542a23a25ff

Subscribe to this mod's changes

research_report is a command published in the GitHub repository arnaudgelas/K-Ops (1 stars, last pushed 17d ago), licensed MIT. It adds 2 tokens to every session and 536 once invoked, about $0.0000 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.

Related

Other commands, from other repositories