phase-summary

phase-summary is a cursor rule for Cursor from hlalljie/agent-workflow-presets. It costs 100 tokens per session, scanned A, original, MIT.

A task-closing rule that requires a phase summary before suggesting a commit. A commit is a saved set of code changes in version control.

In plain words
What is it for?
Use it when a task or work phase is complete and the agent is about to propose a commit.
Why use it?
It prevents the agent from ending work without showing what changed and how it was tested. The owner can review that summary before approving the commit.

Cursor rule for Cursor

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 rules/hlalljie/agent-workflow-presets/phase-summary
Clone the repo
git clone --depth 1 https://github.com/hlalljie/agent-workflow-presets

Made for: Cursor.

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 phase-summary

README.md
[![agentmods](https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/phase-summary.svg)](https://agentmods.dev/rules/hlalljie/agent-workflow-presets/phase-summary)
Your own site
<a href="https://agentmods.dev/rules/hlalljie/agent-workflow-presets/phase-summary"><img src="https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/phase-summary.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 This file is loaded in full into every session.
When invoked 100 The same file — it is already loaded in full.
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 $0.00100 $0.00100
Opus 5 $0.00050 $0.00050
Sonnet 5 $0.00020 $0.00020
Haiku 4.5 $0.00010 $0.00010

Measured 3d ago against content hash 18df0cc7db62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase-summary 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.

.cursor/rules/phase-summary.mdc · 9 lines

What it actually says

Before proposing a commit that closes out a task loop or phase, always run the phase-summary skill first. The summary must be printed in the response before the commit message appears.

Never jump straight to a commit proposal after finishing tasks — the owner must see what was done and how it was tested before approving a commit.

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 · 9 lines · 100 tokens per session scan A 18df0cc7db62

Subscribe to this mod's changes

phase-summary is a cursor rule published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session, about $0.0005 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.