# Decide

> /cs:decide <memo> — Log a decision to two-layer memory via decision-logger. Approved memo becomes durable; raw transcripts kept for reference.

- **Type:** Skill
- **Install:** `agentstack add skill-alexbramall-claude-code-skills-decide`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [AlexBramall](https://agentstack.voostack.com/s/alexbramall)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [AlexBramall](https://github.com/AlexBramall)
- **Source:** https://github.com/AlexBramall/claude-code-skills/tree/main/c-level-advisor/c-level-agents/skills/decide

## Install

```sh
agentstack add skill-alexbramall-claude-code-skills-decide
```

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

## About

# /cs:decide — Log the Decision

**Command:** `/cs:decide `

Logs the founder's decision via the `decision-logger` skill. This is the gate where in-session deliberation becomes durable company memory.

## Pipeline Position

```
/cs:office-hours  →  /cs:brief  →  /cs:boardroom  →  /cs:decide  →  /cs:execute  →  /cs:post-mortem
                                                       ↑ you are here
```

## Two-Layer Memory Model

The `decision-logger` skill maintains two layers:

1. **Raw transcripts** — every boardroom session, every advisor's Phase 2 position, every dissent. Stored under `~/.claude/decisions/raw/`. Reference only, never feeds back automatically.
2. **Approved decisions** — only the founder-signed memos. Stored under `~/.claude/decisions/approved/`. Feeds into future `/cs:office-hours` and `/cs:founder-mode` calls.

This split prevents the system from "remembering" unresolved debates as if they were decisions.

## Input

A board memo file (output of `/cs:boardroom`).

## Workflow

1. Read the memo path
2. Verify it has founder approval (status: APPROVED)
3. Extract structured decision record:
   - Decision title
   - Date decided
   - Option chosen
   - Success + kill criteria
   - Dissent (preserved)
   - Review checkpoint date
4. Append to `~/.claude/decisions/approved/-.md`
5. Update the raw transcript pointer
6. If llm-wiki bridge configured, write to vault (`~/company-vault/10-decisions/`)
7. Schedule auto-revisit (90 days)

## Output Record Format

```markdown
# Decision: 
**Decided:** YYYY-MM-DD
**By:** 
**Memo:** 
**Brief:** 
**Review checkpoint:** YYYY-MM-DD (90d default)

## Decision
**Chose:** 
**Rejected:** 

## Success Criteria (binding)
- 

## Kill Criteria (binding)
- 

## Preserved Dissent
- **:** 
- (preserved verbatim; dissent never erased)

## Next Action
- `/cs:execute` → 90-day plan due 

## Status History
- YYYY-MM-DD: APPROVED
```

## Why Preserved Dissent

The biggest risk in approved decisions is forgetting why someone disagreed. When the kill criteria trigger, the dissent often turns out to have been correct. Preserving it verbatim — not summarized — keeps the company honest at post-mortem time.

## Routing

- `/cs:execute ` — build the 90-day plan
- `/cs:freeze  ` — lock if irreversible
- (Auto-scheduled) `/cs:post-mortem ` — at 90-day checkpoint

## Stale-Decision Audit

`cs-chief-of-staff` runs a weekly stale audit:
- Decisions > 90 days without revisit → flag for `/cs:post-mortem`
- Decisions with kill criteria triggered → flag immediately
- Decisions whose company-context.md basis has changed → flag for re-examination

## Related

- Skill: [`decision-logger`](../../../skills/decision-logger/SKILL.md)
- Agent: [`cs-chief-of-staff`](../../agents/cs-chief-of-staff.md)
- Bridge: [`../../references/llm-wiki-bridge.md`](../../references/llm-wiki-bridge.md)

---

**Version:** 1.0.0

## Source & license

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

- **Author:** [AlexBramall](https://github.com/AlexBramall)
- **Source:** [AlexBramall/claude-code-skills](https://github.com/AlexBramall/claude-code-skills)
- **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-alexbramall-claude-code-skills-decide
- Seller: https://agentstack.voostack.com/s/alexbramall
- 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%.