# Log Decision

> >

- **Type:** Skill
- **Install:** `agentstack add skill-neuroanalytics-data-science-harness-log-decision`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [neuroanalytics](https://agentstack.voostack.com/s/neuroanalytics)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [neuroanalytics](https://github.com/neuroanalytics)
- **Source:** https://github.com/neuroanalytics/data-science-harness/tree/main/plugins/project/skills/log-decision

## Install

```sh
agentstack add skill-neuroanalytics-data-science-harness-log-decision
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Skill: log-decision

Capture the *why* behind a choice so future-you (or a collaborator, or a reviewer) can reconstruct
the reasoning, not just the result. Decisions are recorded as tracked log entries in the ledger —
provenance for judgment, alongside the provenance for computation. You delegate the save to the
**datalad doer**.

## When to use
- A non-obvious methodological or design choice was made (a model, an exclusion criterion, a tool,
  dropping/keeping a comparison) and its rationale should be preserved.
- Do NOT use to record a computation (`analyze/run-comparison` already provenances that) or to make
  a formal commitment (`govern/preregister` / `govern/obligations`).

## Steps
1. **Capture the decision** — get: the `decision` (what was chosen), the `rationale` (why), the
   `alternatives` considered and why they were not chosen, and the `scope` (which branch/comparison/
   product it affects, if any).
2. **Append to the log** — one entry to `project.yaml` `log[]`:
   `{ ts, op: log-decision, stage: manage, note: "DECISION:  — WHY:  — ALT: ", branch:  }`.
   Keep the note self-contained so the reasoning is legible from the log alone.
3. **Save** — delegate to the datalad doer: "save: `datalad save -m 'log-decision: '`."
4. **Report** — confirm the decision was recorded and on which branch.

## Constraints
- Record the decision *and* its rationale and alternatives — a decision without its "why" is not
  worth logging; do not reduce it to a bare statement.
- Record honestly: capture the actual reasoning, including trade-offs, not a post-hoc justification.
- `log:` is append-only — a reversed decision is a *new* log-decision entry referencing the prior
  one, never an edit of it. Keep the ledger schema-valid; delegate the save to the datalad doer.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [neuroanalytics](https://github.com/neuroanalytics)
- **Source:** [neuroanalytics/data-science-harness](https://github.com/neuroanalytics/data-science-harness)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-neuroanalytics-data-science-harness-log-decision
- Seller: https://agentstack.voostack.com/s/neuroanalytics
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.