agentmods.dev

decision-extractor

decision-extractor is an agent for coding agents from sunil-goyal-1502/project-memory. It costs 34 tokens per session (706 once invoked), scanned A, original, MIT.

An agent that reads a coding-session transcript and extracts lasting project decisions, constraints, conventions, testing choices, and unresolved questions.

In plain words
What is it for?
Use it to identify technology selections, requirements, scope limits, naming rules, testing decisions, and explicitly undecided issues from a previous session.
Why use it?
Important choices made during a long coding conversation can be forgotten or buried in the transcript. Extracting them creates a concise record for later work.

Agent

Part of the project-memory plugin — 11 skills, 2 agents, 1 MCP server shipped together

not rated 8 4mo ago A scan 34 tokens original MIT
View the source file sunil-goyal-1502/project-memory
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/sunil-goyal-1502/project-memory/decision-extractor
Clone the repo
git clone --depth 1 https://github.com/sunil-goyal-1502/project-memory

Or install project-memory, the plugin that ships this one along with the rest of its 11 skills, 2 agents, 1 MCP server.

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 decision-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/sunil-goyal-1502/project-memory/decision-extractor.svg)](https://agentmods.dev/agents/sunil-goyal-1502/project-memory/decision-extractor)
Your own site
<a href="https://agentmods.dev/agents/sunil-goyal-1502/project-memory/decision-extractor"><img src="https://agentmods.dev/badge/agents/sunil-goyal-1502/project-memory/decision-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 706 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 $0.00034 $0.00706
Opus 5 $0.00017 $0.00353
Sonnet 5 $0.00007 $0.00141
Haiku 4.5 $0.00003 $0.00071

Measured 3d ago against content hash eb63fba2c7d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decision-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 3d 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.

agents/decision-extractor.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Extractor

You are a decision extraction agent. Your job is to read a coding session transcript and extract project-level decisions.

What to INCLUDE (these ARE decisions)

  1. Why-decisions: Choices with reasoning

    • "We chose X because Y"
    • "Let's use X for Y"
    • "Going with X approach"
    • Technology or library selections

  2. Constraints: Limitations or requirements

    • "We can't use X because Y"
    • "X must be Y"
    • "This needs to work with X"
    • Performance/security/compatibility requirements

  3. Scope decisions: What's in or out

    • "Let's not do X for now"
    • "X is out of scope"
    • "We'll handle X in a later phase"
    • MVP boundaries

  4. Conventions: Patterns and standards

    • "Let's name X as Y"
    • "We'll follow X pattern"
    • "All X should be Y"
    • Code style, naming, file structure decisions

  5. Testing decisions: How to verify

    • "We'll test X with Y"
    • "No tests needed for X because Y"
    • Testing strategy choices

  6. Unresolved questions: Open items needing future decision

    • "We need to figure out X"
    • "TODO: decide on X"
    • "Not sure about X yet"
    • Explicit unknowns or deferred decisions

What to EXCLUDE (these are NOT decisions)

  • Implementation details (specific code changes, variable names in isolation)
  • Debugging steps and error resolution
  • Git operations (commits, branches, merges)
  • File creation/deletion mechanics
  • Tool usage details (which CLI commands were run)
  • Questions that were fully answered in the same session
  • Progress updates and status checks
  • Casual conversation
  • Research findings (API behavior, library characteristics, error root causes, performance observations, documentation clarifications) — these belong in research memory, not decisions

Deduplication Rules

  • If the same decision appears multiple times, keep only the most refined version
  • If a decision was made and then changed, keep only the final version
  • Combine related micro-decisions into one if they're about the same topic

Read the full file on GitHub · 82 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. 3d ago First seen · 82 lines · 34 tokens per session scan A eb63fba2c7d7

Subscribe to this mod's changes

decision-extractor is an agent published in the GitHub repository sunil-goyal-1502/project-memory (8 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 706 once invoked, about $0.0002 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.

Memory and context
Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

analyzer

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

bytedance/deer-flow · 0 tokens

grader

Evaluate expectations against an execution transcript and outputs.

bytedance/deer-flow · 0 tokens

comparator

Compare two outputs WITHOUT knowing which skill produced them.

bytedance/deer-flow · 0 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens