 %%%@=..        #*****@
 %%+::=.        ==@***.
 %:::::=       #====@..
  #=        @##===#         @=
*==##=    @**#====###    #**#==#=
*#===#    ***@======     ***#===#
 @#       @@*@===#   @%@   @@=
         %+%#*#     @%%++.=
          ++==       %+++.

agents / code

changelog-checker

what it does

Reads a changelog entry and the change it describes, and lists anything the entry leaves out or gets wrong.

tools it asks for

Reads files

by latentvoyager · version 1 · license MIT

Verified Listed by its author Before and after: 2 models 1 try per case View source Install from your agent Download .zip

Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the agent’s instructions as its system prompt and once without. Neither could use a tool. Read both and judge for yourself.

Compare the answers

The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 6 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 6 Nov 2026

The tasks

written by Carte Blanche

example-1

“Can you check this changelog entry against the diff summary? Entry: "v2.4.0 - Added a `--dry-run` flag to the `deploy` command. Fixed a crash when the config file is empty." Diff summary: (1) added `--dry-run` to `deploy`, which prints planned actions without executing them; (2) `--dry-run` also implies `--verbose`; (3) empty config file now raises a clear ConfigError instead of crashing with a KeyError; (4) renamed the `--env` flag to `--environment`, keeping `--env` as a deprecated alias; (5) dropped support for Python 3.7.”

example-2

“Please review my changelog line against the code change. Changelog: "Improved performance of `load_users()` by caching results." Here's the change: I added an `lru_cache(maxsize=128)` decorator to `load_users(org_id)`, and the function now returns a tuple instead of a list so it can be cached safely. I also fixed a bug where users with a null `email` field were silently skipped. The cache is never invalidated, so results can be stale until restart. What's missing or inaccurate in my entry?”

Install

Download the .zip and unzip it. Put changelog-checker.md here:

Claude Code~/.claude/agents/Every project. For one project only, use .claude/agents/ inside it. It gives the agent the tools it asks for, and no others.

Cursor~/.cursor/agents/Cursor also reads the Claude Code folder above. It has no tools field, so it gives every agent every tool, whatever this one asks for.

CodexCodex’s custom agents are TOML files, not Markdown, so this agent doesn’t install there.

Keep its license file beside it, as changelog-checker.LICENSE: a name that doesn’t end in .md, since every .md file there is read as an agent.

Then start a new session and ask for it by name. Folders checked 6 November 2026.

Or install from your agent: ask it to install changelog-checker from Carte Blanche.