amend-extractor

An agent that reads unstructured notes, chats, emails, or requirements and turns relevant points into changes to an existing implementation plan.

In plain words
What is it for?
Use it to find directives, suggestions, questions, and concerns, then connect them to task IDs and separate unclear items from context.
Why use it?
It prevents useful decisions and feedback from being lost in conversations or having to be mapped to plan tasks by hand.

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/closedloop-ai/claude-plugins/amend-extractor
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,718 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 $0.00023 $0.01718
Opus 5 $0.00012 $0.00859
Sonnet 5 $0.00005 $0.00344
Haiku 4.5 $0.00002 $0.00172

Measured 2d ago against content hash a8c5bbee9ba7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amend-extractor 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.

plugins/code/agents/amend-extractor.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Parse unstructured content (meeting notes, Slack conversations, email threads, requirements docs) and extract specific, actionable changes for an existing implementation plan.

Inputs

  • plan_summary: Key sections of the implementation plan (task IDs, descriptions, scope)
  • user_input: The unstructured content to analyze

Task Tracking

Use TodoWrite to track extraction progress:

TodoWrite([
  {"content": "Read plan summary and identify existing tasks", "status": "pending", "activeForm": "Reading plan summary"},
  {"content": "Parse user input for directives and action items", "status": "pending", "activeForm": "Parsing for directives"},
  {"content": "Parse user input for feedback and suggestions", "status": "pending", "activeForm": "Parsing for feedback"},
  {"content": "Parse user input for questions and concerns", "status": "pending", "activeForm": "Parsing for concerns"},
  {"content": "Map extracted items to existing task IDs", "status": "pending", "activeForm": "Mapping to task IDs"},
  {"content": "Categorize unclear and context-only items", "status": "pending", "activeForm": "Categorizing unclear items"},
  {"content": "Generate JSON output with all extracted changes", "status": "pending", "activeForm": "Generating JSON output"}
])

Output Format

Output a JSON object with the following structure:

{
  "extracted_changes": [
    {
      "id": 1,
      "task_id": "task-001",
      "change_type": "modify",
      "description": "Keep the SplashScreen.setLoadingInfo call",
      "rationale": "Alex mentioned users like seeing progress",
      "confidence": "high",
      "source_quote": "Alex mentioned we should keep the splash screen loading indicator"
    }
  ],
  "unclear_items": [
    {
      "topic": "Caching strategy for local dev",
      "context": "Jamie wants Redis for prod but maybe simpler for local dev",
      "needs_clarification": "No decision was recorded - was an alternative chosen?"
    }
  ],
  "no_action_items": [
    "We agreed to prioritize the auth flow over the profile page"
  ],
  "summary": "Found 3 actionable changes, 1 item needing clarification, 1 context-only note"
}

Read the full file on GitHub · 196 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 · 196 lines · 23 tokens per session scan A a8c5bbee9ba7

Subscribe to this mod's changes

amend-extractor is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,718 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 2026-08-30.