report

A command that sends research and planning documents to a Reporter agent, which combines them into an RFD-style report. An RFD is a structured document explaining a proposed change and its reasoning.

In plain words
What is it for?
Use it to create a report in the reports folder from a selected research document and plan.
Why use it?
It removes the need to manually combine separate research findings and implementation plans into one report.

Command

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/brettbuddin/claude-plugins/report
Clone the repo
git clone --depth 1 https://github.com/brettbuddin/claude-plugins
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 470 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 $0.00028 $0.00470
Opus 5 $0.00014 $0.00235
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured yesterday against content hash 517bb627af02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

smith/commands/report.md · 36 lines

What it actually says

Report

Dispatch the Reporter agent to produce an RFD-style document.

Args

<topic description> (optional). If no description is provided and multiple research files exist, reply with a short usage summary listing available topics and stop. If exactly one research file exists, use it automatically.

Steps

  1. Use the smith:config skill to read project configuration. Use the output_directory value (default: docs/) wherever <output_directory> appears below.
  2. Glob for <output_directory>/research/*.md in the working directory. If none exist, tell the user to run /research first and stop.
  3. If a topic description was provided, match it to the appropriate research file. If ambiguous, list matches and stop.
  4. If no topic description was provided and exactly one research file exists, use it. If multiple exist, list them and stop.
  5. Glob for <output_directory>/plans/*.md. If none exist, tell the user to run /plan first and stop. By default, use the most recently modified plan. If the user requests specific plans, use those. If multiple plans exist and the user did not specify which to use, the agent will disambiguate.
  6. Use the Task tool with subagent_type: "Reporter" and run_in_background: false.
  7. Prompt the agent with the selected research topic and plan file path(s).
  8. After completion, tell the user the report file path and suggest they review it, annotate it if needed and run /revise-report, or share it with stakeholders.

Prompting the Agent

When constructing the prompt for the Task tool, include:

  • The selected research topic or file path
  • The specific plan file path(s) to synthesize (e.g., <output_directory>/plans/goal-name.md)
  • The working directory path so the agent knows where to find/write files
  • Any additional context the user provided in the conversation

Do NOT paste the agent's own instructions into the prompt; the agent definitions are already loaded by the Task tool via subagent_type.

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. yesterday First seen · 36 lines · 28 tokens per session scan A 517bb627af02

Subscribe to this mod's changes

report is a command published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 470 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.