Skip to content
Agentmart
Submit a tool

decision-log

Keep an auditable record of consequential choices and evidence.

Skill by wcygan

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/wcygan-decision-log

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Keep an auditable record of consequential choices and evidence. Use for long-running work, handoffs, or decisions reviewers must reconstruct.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/decision-log

What's inside

Skill name
decision-log
Description
Keep an auditable record of consequential choices and evidence. Use for long-running work, handoffs, or decisions reviewers must reconstruct.
License
MIT
Metadata
kind: component · maintenance: local · upstream-path: pstack/skills/show-me-your-work · upstream-author: Lauren Tan · upstream-revision: 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8 · upstream-repository: https://github.com/cursor/plugins
Instructions
21 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • LICENSE.txt · references/

SKILL.md (first lines)

# Decision log

1. Choose one durable task-local log outside installed skills. Reuse an existing
   log for the same work; distinguish each run or author.
2. Append a row at decisions and checkpoints with time, run, phase, decision,
   reason, evidence pointer, and result. Skip routine actions that change no decision.
3. Link actual artifacts, checks, revisions, or observations. Keep secrets and
   unrelated private history out of the record. If using a spreadsheet-readable
   format, escape delimiters and formula-leading characters in untrusted cells.
4. Correct mistakes with superseding entries so prior reasoning remains visible.
5. Before handoff, resolve evidence pointers and compare this run's claims with
   available execution records. Mark missing records as audit limitations. Seek
   an independent audit when warranted and available; label self-review accurately.

Done when another reader can reconstruct important choices and their outcomes,
including abandoned approaches and uncertainty. Preserve the log through cleanup;
commit or publish it only within the task's authorized scope.

Adapted from pstack; [license and attribution](references/LICENSE.txt).

From wcygan/agent-skills, MIT.

More from wcygan/agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 14, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from wcygan

Cite this page

decision-log skill. Agent Mart. https://agentmart.dev/skills/wcygan-decision-log (last updated 2026-10-24)