Is the Agent Log skill free?

Yes. The skill itself is free from denysdovhan/agents. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Log SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Agent Log?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Log with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Log

Keeps a repo decision journal agents must read before changing covered code

by denysdovhan · denysdovhan/agents

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Aug 10, 2026
Environment: Claude Code 2.x (agent harness)

Built a repo whose log already contained a finalized entry choosing Redis for the job queue, then asked for a write-up of the opposite decision. Without the skill the agent produced a readable page that never mentioned the decision it was reversing and left index.md stale, so the new entry was effectively invisible; the skill's two prescribed grep commands surfaced the contradicting entry immediately and the run linked back to it, kept the frozen entry byte-identical, and opened the new one as wip rather than done. A 22-point conformance check scored the plain write-up 4/22 and the skill version 22/22. Note the upstream rename: the skill formerly published as design-log is now agent-log, and the old path no longer exists in the repo.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Agent Log does

Maintains .agents/log, a version-controlled journal of product and engineering decisions co-owned by the developer and the agent, with a fixed entry format, a wip/done lifecycle and an index table. Before non-trivial changes it makes the agent grep prior entries by related_paths and keywords, treat finalized entries as binding, and surface conflicts instead of silently reversing them. Triggers on explicit log requests and on feature work inside a repo that already has .agents/log; it never initializes the log on its own.

How to install Agent Log

git clone https://github.com/denysdovhan/agents.git
mkdir -p ~/.claude/skills
cd agents && cp -r skills/agent-log ~/.claude/skills/agent-log

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Log

/agent-log Keeps a repo decision journal agents must read before changing covered code

It also activates on plain-language prompts like these:

Log our decision to move background jobs to Postgres pg-boss
Write a .agents/log entry reversing the Redis job queue decision
Check prior agent-log entries for context before this refactor

Frequently asked questions

Is the Agent Log skill free?: Yes. The skill itself is free from denysdovhan/agents. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Log work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Aug 10, 2026. Verdict: Tested · Works. Built a repo whose log already contained a finalized entry choosing Redis for the job queue, then asked for a write-up of the opposite decision. Without the skill the agent produced a readable page that never mentioned the decision it was reversing and left index.md stale, so the new entry was effectively invisible; the skill's two prescribed grep commands surfaced the contradicting entry immediately and the run linked back to it, kept the frozen entry byte-identical, and opened the new one as wip rather than done. A 22-point conformance check scored the plain write-up 4/22 and the skill version 22/22. Note the upstream rename: the skill formerly published as design-log is now agent-log, and the old path no longer exists in the repo.
What is the Agent Log SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Agent Log?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Log with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.