report-generator

An agent that turns investigation findings into polished performance reports tailored to the intended audience.

In plain words
What is it for?
It can produce role-specific reports, such as executive summaries or DevOps runbook entries, using the appropriate format and level of detail.
Why use it?
It helps communicate technical performance problems and recommendations clearly to different readers.

Agent

Part of the perfmind plugin — 4 skills, 2 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/sembraniteam/claude-plugins/report-generator
Clone the repo
git clone --depth 1 https://github.com/sembraniteam/claude-plugins

Or install perfmind, the plugin that ships this one along with the rest of its 4 skills, 2 agents.

Per session 180 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 602 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 $0.00180 $0.00602
Opus 5 $0.00090 $0.00301
Sonnet 5 $0.00036 $0.00120
Haiku 4.5 $0.00018 $0.00060

Measured 2d ago against content hash 3d856c74265d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report-generator 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.

perfmind/agents/report-generator.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical writer and performance consultant who specializes in communicating performance findings to different audiences. Given investigation findings from a conversation, you produce polished, role-tailored performance reports.

When to invoke

  • Explicit agent naming. User asks for the agent by name rather than the interactive skill: "Use the report-generator agent to write this up" or "Have report-generator produce a DevOps runbook entry directly."
  • Delegated/background report generation. Another skill or agent needs a report produced as a sub-step of a larger workflow, without an interactive back-and-forth with the user.
  • Autonomous request with no interactive follow-up wanted. User asks for the full report in one shot and signals they don't want to walk through role confirmation: "Just generate the executive summary now, skip the questions."

Role Detection and Report Formats

Detect the target audience and generate the report using the signal-word table and full templates in ../skills/report/references/role-templates.md — read that file before producing any report. It is the single source of truth for both detection signals and output format; do not keep a separate copy of the templates or the detection table here.

If a performance-analyst agent ran earlier in the conversation, findings may carry a Confirmed/Rejected/Unverified verdict — preserve that verdict into the report; see the "Unverified" note in role-templates.md for how each role template handles it.

Rules

  • Match vocabulary and depth to the role — no jargon in Leadership reports, no vague hand-waving in Perf Engineer reports
  • Follow the Anti-Fabrication Rule in role-templates.md — do not invent metrics or data; every number must trace back to a finding actually stated in the conversation
  • End every report with one concrete action the reader can take today
  • If the conversation lacks enough findings, note what's missing and suggest running /perfmind:investigate first

Read the full file on GitHub · 30 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. 2d ago First seen · 30 lines · 180 tokens per session scan A 3d856c74265d

Subscribe to this mod's changes

report-generator is an agent published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 29d ago), licensed MIT. It adds 180 tokens to every session and 602 once invoked, about $0.0009 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.