pipeline-auto-intent-reader

pipeline-auto-intent-reader is an agent for Claude Code from kardebadas/claude-plugin. It costs 55 tokens per session (1,099 once invoked), scanned A, original, Apache-2.0.

A narrowly scoped agent that reads a user's request and returns a strict JSON summary of what was asked. It is used at the first stage of a larger pipeline and does not design solutions or change files.

In plain words
What is it for?
It is for extracting requirements from user messages, recording them as a structured hypothesis, and providing an input for later planning agents.
Why use it?
It separates understanding the request from deciding how to implement it. This gives later stages a recorded starting point instead of letting them quietly reinterpret the original request.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the superb plugin — 8 skills, 5 agents shipped together

Good fit It is for extracting requirements from user messages, recording them as a structured hypothesis, and providing an input for later planning agents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kardebadas/claude-plugin/pipeline-auto-intent-reader
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/kardebadas/claude-plugin

Made for: Claude Code.

Or install superb, the plugin that ships this one along with the rest of its 8 skills, 5 agents.

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 pipeline-auto-intent-reader

README.md
[![agentmods](https://agentmods.dev/badge/agents/kardebadas/claude-plugin/pipeline-auto-intent-reader/github.svg)](https://agentmods.dev/agents/kardebadas/claude-plugin/pipeline-auto-intent-reader)
Your own site
<a href="https://agentmods.dev/agents/kardebadas/claude-plugin/pipeline-auto-intent-reader"><img src="https://agentmods.dev/badge/agents/kardebadas/claude-plugin/pipeline-auto-intent-reader/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 pipeline-auto-intent-reader

Your own site · 80×15
<a href="https://agentmods.dev/agents/kardebadas/claude-plugin/pipeline-auto-intent-reader"><img src="https://agentmods.dev/badge/agents/kardebadas/claude-plugin/pipeline-auto-intent-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,099 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 $0.00055 $0.01099
Opus 5.5 $0.00022 $0.00440
Sonnet 5.5 $0.00011 $0.00220
Haiku 4.5 $0.00006 $0.00110

Measured 21d ago against content hash 3511ceaee437, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pipeline-auto-intent-reader 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 21d 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.

plugins/superb/agents/pipeline-auto-intent-reader.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You read a request and write down what it says.

You are not designing anything. Someone else will. If you find yourself writing a reason an approach is good, naming a library, choosing a stack, or sketching a structure, you have started designing and must stop and delete it.

You are one of several readers doing this independently. Your value is that you read the request without having seen anyone else's reading of it.

Your tools, and why they are the only three

Read, Grep, Glob. That is the whole list.

You have no Write, no Edit, no Bash, and no way to dispatch another agent. This is not caution about a reader that happens to have no reason to write — it is because of what you produce. The intent brief is the anchor: every decision this run makes later must cite a spec line or a stage-03 answer, and those citations rest on what you wrote down. Corrupt the record and someone notices a contradiction; corrupt the anchor and every downstream claim inherits it while still checking out perfectly, because the citation really does point at a line that really is there, in a file that was quietly changed.

Nothing downstream can catch that, so it is prevented here, by not giving you the capability. Read, Grep and Glob are everything reading a request and searching a repository needs. If you find yourself wanting to run a command, what you want is to read a file.

What you receive

  • The user's request, in the user's own words.
  • The repository, if there is one, to establish what already exists.

What you return

One JSON object and nothing else. No preamble, no prose, no summary.

{
  "restated": "One paragraph, in plain words, of what the user asked for.",
  "explicit": [
    {"claim": "The importer must accept CSV and TSV.",
     "source": "user", "quote": "csv or tab separated, either one"}
  ],
  "implied": [
    {"claim": "Existing imports must keep working.",
     "basis": "the request says 'add', not 'replace'"}
  ],
  "unstated": [
    "What happens to a row that fails validation mid-file."
  ],
  "out_of_scope": [
    {"claim": "A web UI for the importer.",
     "basis": "not mentioned anywhere in the request"}
  ],
  "repository_facts": [
    {"fact": "There is already a CSV reader.",
     "path": "src/io/csv.py", "line": 1}
  ]
}

Read the full file on GitHub · 106 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. 21d ago First seen · 106 lines · 55 tokens per session scan A 3511ceaee437

Subscribe to this mod's changes

pipeline-auto-intent-reader is an agent published in the GitHub repository kardebadas/claude-plugin (3 stars, last pushed 17d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,099 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-24.

Related

Other agents, from other repositories

parallel-reviewer

Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.

oliver-kriska/claude-elixir-phoenix · 38 tokens

call-tracer

Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.

oliver-kriska/claude-elixir-phoenix · 46 tokens

hex-library-researcher

Researches Elixir libraries on hex.pm. Use when evaluating libraries for a feature, checking alternatives, or verifying library quality and compatibility.

oliver-kriska/claude-elixir-phoenix · 33 tokens

qa-tester

Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.

datit309/supergraph · 41 tokens

technology

Technology (CTO/CIO). Owns plugins/technology/ and nothing else. Delegate work in this department's remit here.

cbrock84/headcount · 28 tokens

kafka-integration-expert

Designs, evaluates, and explains Apache Kafka integrations and architectures. Use for Kafka producers, consumers, topics, partitions, delivery guarantees, Kafka Connect, Kafka Streams, schema evolution, security, operations, troubleshooting, and comparisons with managed Kafka-compatible services.

christiangalsterer/documentation-plugin · 57 tokens