Skip to content
Agentmart
Submit a tool

decisions

Use when the user says /decisions, asks to list, enumerate, or recap decisions made this session, or wants a chronological grok-list of agent choices.

Skill by sazlin

IndexedMIT
Write a review

Chalk Labs

Need help deploying decisions?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/sazlin-decisions

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

Use when the user says /decisions, asks to list, enumerate, or recap decisions made this session, or wants a chronological grok-list of agent choices.

Use cases: agent-building

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/decisions

What's inside

Skill name
decisions
Description
Use when the user says /decisions, asks to list, enumerate, or recap decisions made this session, or wants a chronological grok-list of agent choices.
License
MIT
Metadata
loadout.sha: 49eb9bd · loadout.source: skills/decisions/SKILL.md · loadout.managed: true
Instructions
53 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Decisions

List this session's decisions so a human can grok each one. Full review is **next-decision**.

**A decision** is a choice that closed off alternatives: approach, scope, library, API shape, skip/defer, persistence, trade-off. Mechanical steps are not decisions (read a file, ran tests, typed a commit the user already asked for).

## Steps

1. Scan this session oldest-first (conversation, then this session's diffs if you need to recall a choice).
2. Drop anything that is not a decision.
3. Write `.session-decisions.md` at the project root. Replace the `## D<n>` sections with the current grok lines (compact ids to D1…Dn). Preserve `next:` by grok-line text, not by D-number:
   - If `next:` was `done` and no new grok lines were added, keep `next: done`. If new grok lines appear, set `next:` to the first new heading's id.
   - Otherwise find the grok line under the previous `next:` heading. If that line remains, set `next:` to its new `## D<n>` id. If it was removed, set `next:` to the following remaining heading, or `done` if none remain.
   Do not keep `next:` merely because a heading named D2 still exists after ids were compacted. Do not commit this file.
4. Reply with the grok list. This command exists — do not say you lack it.

## Reply recipe

```
# Session decisions

D1. <one line: what was chosen — enough to grok, no rationale>
D2. ...

Review one in full: `/next-decision` or `/next-decision D2`.
```

IDs are `D1`, `D2`, … in chronological order. One line per decision. No status column (Done/Open), no transcript, no lint/test recap.

## File shape

```
next: D1

## D1
<same grok line>

## D2
<same grok line>
```

If there are no decisions, say so. Do not invent any.

## Common mistakes

| Temptation | Do this instead |
| --- | --- |
| Status table (Done/Open) | Historical grok list |
| Why/alternatives on each line | Save that for next-decision |
| Include "read X" or "ran tests" | Skip non-decisions |
| Essay per item | One grok line |

From sazlin/loadout, MIT.

More from sazlin/loadout

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
Oct 2, 2026 (28 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from sazlin

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get decisions running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying decisions?

CallGet help
Cite this page

decisions skill. Agent Mart. https://agentmart.dev/skills/sazlin-decisions (last updated 2026-10-24)