AgentMeasure

Audit your Codex and Claude Code logs

WHO USES ITDevelopers who use Codex or Claude Code daily, and anyone building or maintaining agent tooling.

Install to use

Reads your Codex and Claude Code session logs and surfaces repeated failures and retries, with the evidence attached.

INSTALL

START IN 5 MINUTES ↓

The AgentMeasure landing page: "The open yardstick for agent metrics" on the left, and a terminal panel on the right showing checks marked PASS, FAIL and UNPROVABLE.

TESIGN TAKE

Marking what it cannot prove as UNPROVABLE instead of quietly writing zero is what makes the numbers worth trusting.

Activity and discovery evidence

★ 216▲ 2 HNAs of 09-22 03:00 UTC

216 stars · checked on GitHub 09-19 11:09 UTC GitHub check 68 h late · no 7-day star increase observed (GH Archive) (as of 09-22 03:00 UTC) · 2 Show HN points observed 09-22 01:35 UTC

NEW 0h OLD WHEN SEEN

AT A GLANCE

LICENSE: MIT
USAGE: Use, change and redistribute, commercially too. Keep the notice.
LANGUAGE: Python
PLATFORM: cli
ACTIVITY: last commit 2 days ago (2026-09-19) · latest release [unconfirmed] As of 09-19 11:09 UTC
COMMUNITY: contributors [unconfirmed] · open issues [unconfirmed] · made by: [unconfirmed] Reference time unavailable
SOURCES: Show HN
OPEN SOURCE: YES
FIRST SEEN: 2026-09-19 10:09 UTC
CATEGORY: DEV TOOLS · AI

A summary, not legal advice.

WHY IT MATTERS

An agent that edits the same file over and over, or hits one failed tool call after another, is easy to miss when it is buried in a log. AgentMeasure reads the session logs you already have and finds duplicate records, retry chains and consecutive tool failures — and when the evidence is not there it says UNPROVABLE rather than inventing a zero.

BUILD FROM THIS

Written in Python and published on PyPI, so pipx runs it with no repository checkout. There is a demo mode with no personal logs needed, a check command over the last seven days, and a flag to force the Claude Code adapter. All analysis runs locally with no network calls, and the result is a terminal summary plus a local HTML report.

WHO IT'S FOR

Developers who use Codex or Claude Code daily, and anyone building or maintaining agent tooling.

START IN 5 MINUTES

# Run pipx run agentmeasure demo first to see it on a synthetic example.

CAVEATS

It is built around the log formats Codex and Claude Code write, so sessions from other tools are not covered, and the repository marks its billing/settlement feature (settle) as still a concept.

RECEIPT

FIRST SEEN: 2026-09-19 10:09 UTC
AT SOURCE: 2026-09-19 09:16 UTC
KEPT: 2026-09-22 05:53 UTC
CREATED → FIRST SEEN: 0h
WHEN FIRST SEEN: 216 ★
SOURCES: Show HN

The same facts in machine-readable form — View as Markdown · JSON

SIMILAR TOOLS

Up to five from DEV TOOLS by ★ total: edited entries first, then repository cards; this entry is highlighted. Drawn from the same stored snapshot as the rankings — a comparison, not a recommendation. As of 09-22 03:00 UTC

NAME	★ TOTAL	▲ 7d	LICENSE	PLATFORM	LAST PUSH
eccSkills, memory and security for agents	★ 265k	▲ +413	MITpermissive	windows · macos · linux · cli	2026-09-21
DeepSeek HarnessPlugin agent harness for developers	★ 232k	▲ +487	MITpermissive	web · cli	2026-09-17
ponytailMake your agent write less code	★ 144k	▲ +349	MITpermissive	—	2026-09-14
Spec KitSpec-first process for coding agents	★ 138k	▲ +89	MITpermissive	cli · windows · macos · linux	2026-09-21
AgentMeasureAudit your Codex and Claude Code logsTHIS ENTRY	★ 216	—	MITpermissive	cli	2026-09-19

TIMELINE

2026-08-16 02:47 UTCRepository created
2026-09-19 09:16 UTCShow HN post ↗
2026-09-19 10:09 UTCFIRST SEEN BY TESIGN
2026-09-22 05:53 UTCPublished on TESIGN

SAME DAY

01
ZCode
Run multiple coding agents from one app
A coding workspace that runs several AI agents at once and drives a goal to completion.
Use in the browser
★ 5.1k▲ +64 / 7d09-22 03:00 UTC
02
Try Omarchy for Windows
Try the Omarchy Linux desktop on Windows
An app that boots the real Omarchy Linux desktop inside a window on Windows — no VM software to install.
Install to use
★ 440▲ 5 HN09-22 03:00 UTC
03
hibi
A markdown notes app with a graph view
A desktop Markdown editor that also draws a graph of how your notes connect.
Install to use
★ 14▲ 5 HN09-22 03:00 UTC
04
tfm
Drag and drop files inside your terminal
A terminal file manager built for the mouse — drag, drop, dual panes, thumbnails.
Install to use
★ 136▲ +9 / 7d09-22 03:00 UTC
06
package-doctor
Find the Python dependency to fix first
Scans Python dependencies and tells you which are being exploited now — and which have no one left to fix them.
Install to use
★ 8▲ 4 HN09-22 03:00 UTC
07
pokertools-arena
Watch AI models play poker at one table
Seats several OpenAI-compatible models at the same poker table and lets you watch every decision as a spectator.
Use in the browser
★ 1▲ 2 HN09-22 03:00 UTC
08
Roastbook
Log espresso shots on your own server
A self-hosted coffee journal that reads a photographed bag’s label and fills in the details for you.
Self-host
★ 2▲ 1 HN09-22 03:00 UTC
09
Comic Chat for AI
Turn a ChatGPT chat into a comic strip
A revival of Microsoft’s old Comic Chat that automatically draws a ChatGPT conversation as a comic strip.
Install to use
★ 1▲ 3 HN09-22 03:00 UTC
10
2049 — Mines of Merge
2048 fused with Minesweeper in a dungeon
You are the tile: slide by 2048 rules while dodging Minesweeper-style hidden mines down eight depths.
Use in the browser
★ 0▲ 1 HN09-22 03:00 UTC