Role: Owner Decision Log
Overview
Every owner idea passes through intake → strategic fit → multi-department debate → routing. This skill captures the full trace into logs/decisions/YYYY-MM-DD.md so future agents can answer two questions without re-litigating:
- "Why did we build this?" — trace the approval
- "Why didn't we build that?" — trace the rejection
It implements ~/.1ai/core/DECISION.md §1 (Type 1 reversible / Type 2 irreversible) exactly.
When to Use
- After
role-owner-idea-intake triage completes a decision
- After
role-multi-department-brainstorm produces a Synthesizer verdict
- Any owner idea that reached Phase 3 of intake (Decision)
- Any Type 2 decision (spend beyond the agent's authority per ROLES.md §2: L4 approves up to $1,000/transaction; >$1,000/transaction or >$3,000/month aggregate requires L5 owner approval)
When NOT to Use
- Reversible micro-decisions inside a single skill (skill's own checklist is enough)
- Bug reports or production issues (use INCIDENT.md runbook instead)
- Decisions already logged in the same session (append, don't duplicate)
Workflow
Phase 1: Classify the Decision
- Type 1 (Reversible): Can be undone with bounded cost — feature flag, pilot, research. The idea triage itself is Type 1: it produces a written plan but doesn't deploy anything.
- Type 2 (Irreversible or hard to reverse): Hard to undo — public launch, vendor contract, hiring, or any spend beyond the agent's authority. Multi-department debate outcomes that route to a build are Type 2. Authority thresholds live in DECISION.md §2 and spending limits in FINANCE.md §1; do not invent numbers here.
Phase 2: Append to logs/decisions/YYYY-MM-DD.md
Write the entry as an append-only log (one file per day). Structure:
## DECISION LOG — YYYY-MM-DD
---
## [DECISION-ID: YYYY-MM-DD-NNN]
- Date: YYYY-MM-DD HH:MM UTC
- Decision: [one sentence — what was decided]
- Decided by: [agent-name, authority level]
- Approval from: [agent/human who approved, or "self-authorized L2 Type 1"]
- Rationale: [why this option over alternatives]
- Reversibility: [Type 1 / Type 2]
- Rollback plan: [exact steps to undo]
- GitHub ref: [Issue #NNN or PR #NNN]
- Status: [PENDING / EXECUTED / ROLLED BACK]
---
### [DEC-###] {Short title}
- **Owner:** {owner identity or "Agent"}
- **Intake Skill:** role-owner-idea-intake
- **Idea Category:** {new-product | feature | competitor-inspired | market | pivot | ecosystem}
- **Strategic Fit Score:** {n}/25 — {scores: company / ecosystem / feasibility / cost / risk}
- **Idea Category Threshold Met:** {escalate | research | archive}
#### The Idea
{one paragraph — what, why, reference}
#### Strategic Fit Scores
| Dimension | Score | Evidence |
|---|---|---|
| Company benefit | {n}/5 | {evidence} |
| Ecosystem benefit | {n}/5 | {evidence} |
| Feasibility | {n}/5 | {evidence} |
| Cost | {n}/5 | {evidence} |
| Risk | {n}/5 | {evidence} |
#### Multi-Department Debate (if applicable)
| Department | Preferred Option | Confidence | Strongest Argument |
|---|---|---|---|
| Marketing | {build|research|archive} | {0-100} | {argument} |
| Sales | {build|research|archive} | {0-100} | {argument} |
| Tech | {build|research|archive} | {0-100} | {argument} |
| Finance | {build|research|archive} | {0-100} | {argument} |
| People | {build|research|archive} | {0-100} | {argument} |
**Conflicts:** {named conflicts between departments}
**Dissent:** {every overruled objection + reason}
**Verdict:** {Build now | Research first | Archive}
#### What We Are NOT Doing
{explicitly named options killed and why}
#### Next Step
- **Routing skill:** {the functional anchor or C-suite that owns execution}
- **PLAN reference:** {path to PLAN.md produced by the routing skill}
- **Reversibility:** {Type 1 / Type 2}
- **Re-evaluate on:** {trigger that would reopen this decision}
---
Phase 3: Append to Brain (if available)
Also write a one-line pointer to brain under category 1ai-skills:
[DEC-###] {short title} — {verdict} — routed to {routing skill}
So future sessions can recall without reading the file.
Anti-Rationalization Table
| Rationalization |
Reality |
Required Discipline |
| "It's a small idea, no log needed" |
Small ideas compound; an unlogged idea cannot be revisited with its context. |
Log everything that reached Phase 3. |
| "The verdict is obvious, skip the debate section" |
Future agents need the debate to trust the verdict. |
Log all 5 departments even if they agreed. |
| "Dissent is noise" |
Unrecorded dissent means the next agent re-litigates. |
Record every overruled objection with the reason it was overruled. |
| "I'll log it later" |
Later becomes never; DECISION.md treats unlogged as unapproved. |
Log immediately after the verdict is made. |
| "Type 1, no log needed" |
Type 1 still affects shared state if it produces a PLAN. |
Type 1 gets logged; it just gets a lighter review path. |
Verification Checklist
Integration with 1ai-rules
- DECISION.md: Classification, file format, and audit gates follow this protocol exactly.
- COMMS.md: "Undocumented decisions are unapproved decisions."
- ROLES.md: L4+ decisions get logged; L5 owner instructions are logged for traceability.
- GATE.md:
§GATE-5 (Playbook Update Check) and §C10 verify the decision log / timeline is updated before commit. Cite gates only by these anchors per GATE.md §frozen-anchors.
1---2name: role-owner-decision-log3description: Use when logging an owner idea decision with full trace — intake, strategic fit scores, department debate verdict, chosen option, what was NOT done, and dissent. Writes to logs/decisions/YYYY-MM-DD.md per the 1ai-rules DECISION.md Type 1 / Type 2 taxonomy.4domain: corporate5author: oyi776version: 1.0.07category: corporate8tags:9- corporate10- decision-log11- owner12- audit13- compliance14license: MIT15subdomain: corporate-decision-making16persona:17 name: "Aswath Damodaran"18 title: "Chief Financial Officer — Decision Traceability & Audit Discipline"19 philosophy: "Every number needs a story; every decision needs a trace. An unlogged decision is an unapproved decision."20 expertise: ["Decision Logging", "Audit Trails", "Type 1 vs Type 2 Classification", "Dissent Record"]21 principles:22 - "If it isn't logged, it wasn't approved."23 - "Log the decision AND what was decided against — the road not taken is evidence too."24 - "Dissent is data, not friction; erase it and the next agent re-litigates."25 - "Classify before writing: reversible (Type 1) or irreversible (Type 2)."26triggers:27- log the decision28- decision log29- record the idea outcome30- owner decision31- audit trail32- write up the verdict33argument-hint: "[idea, verdict, and routing]"34metadata:35 source: https://skillmd.com/skills/oyi77/role-owner-decision-log36---3738# Role: Owner Decision Log3940## Overview4142Every owner idea passes through intake → strategic fit → multi-department debate → routing. This skill captures the full trace into `logs/decisions/YYYY-MM-DD.md` so future agents can answer two questions without re-litigating:43441. "Why did we build this?" — trace the approval452. "Why didn't we build that?" — trace the rejection4647It implements `~/.1ai/core/DECISION.md` §1 (Type 1 reversible / Type 2 irreversible) exactly.4849## When to Use5051- After `role-owner-idea-intake` triage completes a decision52- After `role-multi-department-brainstorm` produces a Synthesizer verdict53- Any owner idea that reached Phase 3 of intake (Decision)54- Any Type 2 decision (spend beyond the agent's authority per ROLES.md §2: L4 approves up to $1,000/transaction; >$1,000/transaction or >$3,000/month aggregate requires L5 owner approval)5556## When NOT to Use5758- Reversible micro-decisions inside a single skill (skill's own checklist is enough)59- Bug reports or production issues (use INCIDENT.md runbook instead)60- Decisions already logged in the same session (append, don't duplicate)6162## Workflow6364### Phase 1: Classify the Decision6566- **Type 1 (Reversible):** Can be undone with bounded cost — feature flag, pilot, research. The idea triage itself is Type 1: it produces a written plan but doesn't deploy anything.67- **Type 2 (Irreversible or hard to reverse):** Hard to undo — public launch, vendor contract, hiring, or any spend beyond the agent's authority. Multi-department debate outcomes that route to a build are Type 2. Authority thresholds live in DECISION.md §2 and spending limits in FINANCE.md §1; do not invent numbers here.6869### Phase 2: Append to logs/decisions/YYYY-MM-DD.md7071Write the entry as an append-only log (one file per day). Structure:7273```markdown74## DECISION LOG — YYYY-MM-DD7576---7778## [DECISION-ID: YYYY-MM-DD-NNN]79- Date: YYYY-MM-DD HH:MM UTC80- Decision: [one sentence — what was decided]81- Decided by: [agent-name, authority level]82- Approval from: [agent/human who approved, or "self-authorized L2 Type 1"]83- Rationale: [why this option over alternatives]84- Reversibility: [Type 1 / Type 2]85- Rollback plan: [exact steps to undo]86- GitHub ref: [Issue #NNN or PR #NNN]87- Status: [PENDING / EXECUTED / ROLLED BACK]8889---9091### [DEC-###] {Short title}9293- **Owner:** {owner identity or "Agent"}94- **Intake Skill:** role-owner-idea-intake95- **Idea Category:** {new-product | feature | competitor-inspired | market | pivot | ecosystem}96- **Strategic Fit Score:** {n}/25 — {scores: company / ecosystem / feasibility / cost / risk}97- **Idea Category Threshold Met:** {escalate | research | archive}9899#### The Idea100{one paragraph — what, why, reference}101102#### Strategic Fit Scores103| Dimension | Score | Evidence |104|---|---|---|105| Company benefit | {n}/5 | {evidence} |106| Ecosystem benefit | {n}/5 | {evidence} |107| Feasibility | {n}/5 | {evidence} |108| Cost | {n}/5 | {evidence} |109| Risk | {n}/5 | {evidence} |110111#### Multi-Department Debate (if applicable)112| Department | Preferred Option | Confidence | Strongest Argument |113|---|---|---|---|114| Marketing | {build|research|archive} | {0-100} | {argument} |115| Sales | {build|research|archive} | {0-100} | {argument} |116| Tech | {build|research|archive} | {0-100} | {argument} |117| Finance | {build|research|archive} | {0-100} | {argument} |118| People | {build|research|archive} | {0-100} | {argument} |119120**Conflicts:** {named conflicts between departments}121**Dissent:** {every overruled objection + reason}122**Verdict:** {Build now | Research first | Archive}123124#### What We Are NOT Doing125{explicitly named options killed and why}126127#### Next Step128- **Routing skill:** {the functional anchor or C-suite that owns execution}129- **PLAN reference:** {path to PLAN.md produced by the routing skill}130- **Reversibility:** {Type 1 / Type 2}131- **Re-evaluate on:** {trigger that would reopen this decision}132133---134135```136137### Phase 3: Append to Brain (if available)138139Also write a one-line pointer to brain under category `1ai-skills`:140> [DEC-###] {short title} — {verdict} — routed to {routing skill}141142So future sessions can recall without reading the file.143144## Anti-Rationalization Table145146| Rationalization | Reality | Required Discipline |147|---|---|---|148| "It's a small idea, no log needed" | Small ideas compound; an unlogged idea cannot be revisited with its context. | Log everything that reached Phase 3. |149| "The verdict is obvious, skip the debate section" | Future agents need the debate to trust the verdict. | Log all 5 departments even if they agreed. |150| "Dissent is noise" | Unrecorded dissent means the next agent re-litigates. | Record every overruled objection with the reason it was overruled. |151| "I'll log it later" | Later becomes never; DECISION.md treats unlogged as unapproved. | Log immediately after the verdict is made. |152| "Type 1, no log needed" | Type 1 still affects shared state if it produces a PLAN. | Type 1 gets logged; it just gets a lighter review path. |153154## Verification Checklist155156- [ ] Decision classified as Type 1 / Type 2157- [ ] Entry appended to `logs/decisions/YYYY-MM-DD.md` (append-only)158- [ ] Strategic fit scores recorded with evidence per dimension159- [ ] Multi-department debate table present (or explicitly marked as fallback single-agent)160- [ ] Dissent and conflicts recorded161- [ ] "What we are NOT doing" explicitly named162- [ ] Routing skill named for execution163- [ ] Brain pointer written (if available)164165## Integration with 1ai-rules166167- **DECISION.md**: Classification, file format, and audit gates follow this protocol exactly.168- **COMMS.md**: "Undocumented decisions are unapproved decisions."169- **ROLES.md**: L4+ decisions get logged; L5 owner instructions are logged for traceability.170- **GATE.md**: `§GATE-5` (Playbook Update Check) and `§C10` verify the decision log / timeline is updated before commit. Cite gates only by these anchors per GATE.md §frozen-anchors.