decision-logger

$npx mdskill add alirezarezvani/claude-skills/decision-logger

Two-layer memory system. Layer 1 stores everything. Layer 2 stores only what the founder approved. Future meetings read Layer 2 only — this prevents hallucinated consensus from past debates bleeding into new deliberations.

SKILL.md

.github/skills/decision-loggerView on GitHub ↗
---
name: "decision-logger"
description: "Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /decision-logger decisions, or checking overdue action items with /decision-logger review. Invoked automatically by the board-meeting skill after Phase 5 founder approval."
license: MIT
metadata:
  version: 1.0.0
  author: Alireza Rezvani
  category: c-level
  domain: decision-memory
  updated: 2026-03-05
  python-tools: scripts/decision_tracker.py
---

# Decision Logger

Two-layer memory system. Layer 1 stores everything. Layer 2 stores only what the founder approved. Future meetings read Layer 2 only — this prevents hallucinated consensus from past debates bleeding into new deliberations.

## Keywords
decision log, memory, approved decisions, action items, board minutes, /decision-logger decisions, /decision-logger review, conflict detection, DO_NOT_RESURFACE

## Quick Start

```bash
python scripts/decision_tracker.py --demo             # See sample output
python scripts/decision_tracker.py --summary          # Overview + overdue
python scripts/decision_tracker.py --overdue          # Past-deadline actions
python scripts/decision_tracker.py --conflicts        # Contradiction detection
python scripts/decision_tracker.py --owner "CTO"      # Filter by owner
python scripts/decision_tracker.py --search "pricing" # Search decisions
```

---

## Commands

| Command | Effect |
|---------|--------|
| `/decision-logger decisions` | Last 10 approved decisions |
| `/decision-logger decisions --all` | Full history |
| `/decision-logger decisions --owner CMO` | Filter by owner |
| `/decision-logger decisions --topic pricing` | Search by keyword |
| `/decision-logger review` | Action items due within 7 days |
| `/decision-logger review --overdue` | Items past deadline |

---

## Two-Layer Architecture

Storage follows the canonical two-layer decision memory (see `../agent-protocol/SKILL.md` → "Decision Memory (Canonical Layout)") — the same layout `/c-level-agents:decide` writes.

### Layer 1 — Raw Transcripts
**Location:** `~/.claude/decisions/raw/YYYY-MM-DD-<slug>.md`
- Full Phase 2 agent contributions, Phase 3 critique, Phase 4 synthesis
- All debates, including rejected arguments
- **NEVER auto-loaded.** Only on explicit founder request.
- Archive after 90 days → `~/.claude/decisions/raw/archive/YYYY/`

### Layer 2 — Approved Decisions
**Location:** `~/.claude/decisions/approved/` — one record per decision (`YYYY-MM-DD-<slug>.md`) plus the append-only index `decisions.md`
- ONLY founder-approved decisions, action items, user corrections
- **Loaded automatically in Phase 1 of every board meeting**
- Append-only. Decisions are never deleted — only superseded.
- Managed by Chief of Staff after Phase 5. Never written by agents directly.

Migration: a legacy `memory/board-meetings/` folder may exist from earlier versions; read it for history but write all new entries to `~/.claude/decisions/`.

---

## Decision Entry Format

```markdown
## [YYYY-MM-DD] — [AGENDA ITEM TITLE]

**Decision:** [One clear statement of what was decided.]
**Owner:** [One person or role — accountable for execution.]
**Deadline:** [YYYY-MM-DD]
**Review:** [YYYY-MM-DD]
**Rationale:** [Why this over alternatives. 1-2 sentences.]

**User Override:** [If founder changed agent recommendation — what and why. Blank if not applicable.]

**Rejected:**
- [Proposal] — [reason] [DO_NOT_RESURFACE]

**Action Items:**
- [ ] [Action] — Owner: [name] — Due: [YYYY-MM-DD] — Review: [YYYY-MM-DD]

**Supersedes:** [DATE of previous decision on same topic, if any]
**Superseded by:** [Filled in retroactively if overridden later]
**Raw transcript:** ~/.claude/decisions/raw/[DATE]-<slug>.md
```

---

## Conflict Detection

Before logging, Chief of Staff checks for:
1. **DO_NOT_RESURFACE violations** — new decision matches a rejected proposal
2. **Topic contradictions** — two active decisions on same topic with different conclusions
3. **Owner conflicts** — same action assigned to different people in different decisions

When a conflict is found:
```
⚠️ DECISION CONFLICT
New: [text]
Conflicts with: [DATE] — [existing text]

Options: (1) Supersede old  (2) Merge  (3) Defer to founder
```

**DO_NOT_RESURFACE enforcement:**
```
🚫 BLOCKED: "[Proposal]" was rejected on [DATE]. Reason: [reason].
To reopen: founder must explicitly say "reopen [topic] from [DATE]".
```

---

## Logging Workflow (Post Phase 5)

1. Founder approves synthesis
2. Write Layer 1 raw transcript → `~/.claude/decisions/raw/YYYY-MM-DD-<slug>.md`
3. Check conflicts against `~/.claude/decisions/approved/decisions.md`
4. Surface conflicts → wait for founder resolution
5. Write the approved record to `~/.claude/decisions/approved/YYYY-MM-DD-<slug>.md` and append to the index `decisions.md`
6. Confirm: decisions logged, actions tracked, DO_NOT_RESURFACE flags added

---

## Marking Actions Complete

```markdown
- [x] [Action] — Owner: [name] — Completed: [DATE] — Result: [one sentence]
```

Never delete completed items. The history is the record.

---

## File Structure

```
~/.claude/decisions/
├── raw/YYYY-MM-DD-<slug>.md        # Layer 1: full transcript per meeting
├── raw/archive/YYYY/               # Raw files after 90 days
├── approved/YYYY-MM-DD-<slug>.md   # Layer 2: one record per approved decision
└── approved/decisions.md           # Layer 2 index: append-only, founder-approved
```

---

## References
- `templates/decision-entry.md` — single entry template with field rules
- `scripts/decision_tracker.py` — CLI parser, overdue tracker, conflict detector

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.