freeze

$npx mdskill add alirezarezvani/claude-skills/freeze

**Command:** `/c-level-agents:freeze <decision-path> <days>`

SKILL.md

.github/skills/freezeView on GitHub ↗
---
name: "freeze"
description: "/c-level-agents:freeze [decision] [days] — Lock a strategic decision for a cooldown period to prevent impulse reversal. Mirrors gstack's safety primitives for the business layer. Use when an irreversible decision was made under pressure — e.g. a layoff plan or multi-year contract — and deserves a cooling-off lock before execution."
---

# /c-level-agents:freeze — Cooldown Lock on a Decision

**Command:** `/c-level-agents:freeze <decision-path> <days>`

Locks a decision for a defined cooldown period. During the freeze, the chief-of-staff router refuses to re-litigate the decision unless a kill criterion explicitly triggers.

Inspired by gstack's `/freeze` and `/guard` safety primitives — adapted from code-scoping to strategic-scoping.

## When to Use

Founders are pattern-matchers; pattern-matching after a tough decision often produces a reversal that's actually just decision fatigue. The freeze enforces a discipline:

- After any **irreversible** or **high-cost-to-reverse** decision (fundraise, layoff, market entry)
- After a **split-vote boardroom** (preserve the call against second-guessing)
- After a **founder gut-feel** override of unanimous advisor consensus (let it run)
- During a **personnel transition** (lock the strategy so the new exec can execute, not redebate)

## Default Freeze Periods

| Decision type | Default freeze |
|---|---|
| Fundraise round size / lead choice | 30 days |
| Pricing change | 60 days |
| Market entry / exit | 90 days |
| Layoff / RIF | 30 days |
| Strategic pivot | 90 days |
| Personnel (exec hire / fire) | 60 days |
| M&A LOI | 30 days |
| Custom | specify in command |

## Workflow

1. Read the decision record
2. Validate it has APPROVED status
3. Apply freeze: write `freeze_until: YYYY-MM-DD` to the decision record
4. Add to active-freezes index at `~/.claude/freezes/active.md`
5. cs-chief-of-staff router now refuses to re-route this topic to the boardroom until:
   - The freeze period expires, OR
   - A kill criterion explicitly triggers

## Output

The decision record is updated in place:

```markdown
# Decision: <title>
...
**Status:** FROZEN
**Frozen until:** YYYY-MM-DD
**Reason for freeze:** <text>
**Override condition:** Kill criterion <name> triggers OR founder issues `/c-level-agents:freeze release` with stated reason
```

The active-freezes index is updated:

```markdown
# Active Freezes
**Updated:** YYYY-MM-DD

| Decision | Frozen until | Override condition |
|---|---|---|
| <decision title> | YYYY-MM-DD | <kill criterion or /c-level-agents:freeze release> |
```

## Override

To unfreeze before the period ends, the founder runs:

```
/c-level-agents:freeze release <decision> <reason>
```

The unfreeze is logged in the decision history (preserved permanently). Forced overrides create a paper trail that surfaces at post-mortem.

## Auto-Override

If a kill criterion in the decision triggers, the freeze auto-releases and the chief-of-staff routes immediately to `/c-level-agents:post-mortem`. The freeze does not protect against reality; it protects against impulse.

## Why This Beats "Just Don't Re-Decide"

Founders have authority. Without an explicit lock + log, every wobble produces a "let's discuss this again" — which is exhausting for advisors and erodes the value of the boardroom. The freeze is **a process**, not a rule; it logs every override so the post-mortem can audit founder discipline.

## Routing

- `/c-level-agents:freeze release` — explicit early release
- `/c-level-agents:post-mortem` — auto-triggered if kill criterion fires
- `/c-level-agents:boardroom` — blocked until unfreeze or expiry

## Related

- Skill: [`decision-logger`](${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/decision-logger/SKILL.md)
- Agent: [`cs-chief-of-staff`](../../agents/cs-chief-of-staff.md) — enforces freezes in routing

---

**Version:** 1.0.0

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receiptsMint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harnessTurn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestratorUse when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memoryUse when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.