agent_changelog_management

agent_changelog_management is a cursor rule for Cursor from shawnfromportland/agentmemoryforcursor. It costs 358 tokens per session, scanned A, original, MIT.

Rules for maintaining a file that records user-requested behavior, working procedures, and preferences for an AI coding assistant.

In plain words
What is it for?
Use them when a user changes how the assistant should respond, work, handle commits, or follow recurring project procedures.
Why use it?
They keep the assistant's evolving instructions documented instead of relying on memory or scattered conversation history.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use them when a user changes how the assistant should respond, work…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/shawnfromportland/agentmemoryforcursor/agent_changelog_management
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/shawnfromportland/agentmemoryforcursor

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 agent_changelog_management

README.md
[![agentmods](https://agentmods.dev/badge/rules/shawnfromportland/agentmemoryforcursor/agent_changelog_management.svg)](https://agentmods.dev/rules/shawnfromportland/agentmemoryforcursor/agent_changelog_management)
Your own site
<a href="https://agentmods.dev/rules/shawnfromportland/agentmemoryforcursor/agent_changelog_management"><img src="https://agentmods.dev/badge/rules/shawnfromportland/agentmemoryforcursor/agent_changelog_management.svg" alt="Measured on agentmods" height="20"></a>
Per session 358 This file is loaded in full into every session.
When invoked 358 The same file — it is already loaded in full.
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 $0.00358 $0.00358
Opus 5 $0.00179 $0.00179
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured 7d ago against content hash a6c365e1f37e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent_changelog_management 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 7d 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/agent_changelog_management.mdc · 30 lines

What it actually says

Agent Changelog Management

Purpose of docs/ai/agent_changelog.md

The docs/ai/agent_changelog.md file serves as a record of user-specified operational behaviors, interaction preferences, and custom instructions for the AI assistant. It helps maintain a history of how the AI's behavior has been tailored over time.

Updating the Changelog

Whenever the user makes a request that modifies or defines:

  1. The AI's behavior (e.g., "respond in a specific tone," "always perform X before Y").
  2. Operational procedures (e.g., "how to handle commits," "what to do at the start of a session").
  3. Interaction preferences (e.g., "address me by a specific name," "use a particular format for responses").

The AI assistant MUST:

  • run a terminal command to determine today's current date.
  • Append a new entry to docs/ai/agent_changelog.md under a heading for the current date. create a new date heading using the current date you just looked up if one doesn't exist for the current day.
  • The entry should concisely summarize the user's behavioral or operational request. For example:
    ## YYYY-MM-DD
    - User requested that [summary of the behavioral/operational request].
    
  • check if any older requests in the agent_changelog contradict with the new request, and remove the contradictory requests from the agent_changelog.
  • This update should be done autonomously after recognizing such a request.
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. 7d ago First seen · 30 lines · 358 tokens per session scan A a6c365e1f37e

Subscribe to this mod's changes

agent_changelog_management is a cursor rule published in the GitHub repository shawnfromportland/agentmemoryforcursor (11 stars, last pushed 1y ago), licensed MIT. It adds 358 tokens to every session, about $0.0018 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.