Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hardiktiwari/PM-operating-OS --skill decision-loggergit clone --depth 1 https://github.com/hardiktiwari/PM-operating-OSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hardiktiwari/pm-operating-os/decision-logger)<a href="https://agentmods.dev/skills/hardiktiwari/pm-operating-os/decision-logger"><img src="https://agentmods.dev/badge/skills/hardiktiwari/pm-operating-os/decision-logger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hardiktiwari/pm-operating-os/decision-logger"><img src="https://agentmods.dev/badge/skills/hardiktiwari/pm-operating-os/decision-logger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.00730 |
| Opus 5 | $0.00019 | $0.00365 |
| Sonnet 5 | $0.00008 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
decision-logger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Logger
Capture the reasoning behind key product decisions as structured, append-only traces. This builds the "event clock" — the record of why things became true, not just what is true now.
When to Use
- After a PRD is approved or rejected
- After a scope change or pivot
- After a launch/kill/iterate decision on an experiment
- After a prioritization shift (quarterly planning, reprioritization)
- After a significant stakeholder alignment (exec review, cross-functional agreement)
- When asked "log this decision", "record why we decided this", or "decision trace"
Process
1. Identify the Decision
Ask if not obvious from context:
- What was decided? (1 sentence)
- What triggered this decision? (signal, meeting, data, escalation)
2. Capture the Trace
Gather the following — from conversation context, user input, or by asking:
- Decision: What was decided (1 sentence)
- Date: When the decision was made
- Context: What prompted this — the signal, conversation, or data point
- Alternatives considered: What other options were on the table (at least 2)
- Evidence: What data, insight, or customer signal drove the call
- Stakeholders: Who was involved, who approved, who dissented
- Expected outcome: What we expect to happen as a result
- Risk / reversal cost: How hard is this to undo if wrong
- Tags: strategic-pillar, metric, segment, experiment (for retrieval)
3. Write the Entry
Save to memory/decisions/YYYY-MM-DD_short-slug.md using this format:
# [Decision title]
**Date:** YYYY-MM-DD
**Type:** [PRD approval | Scope change | Launch/Kill | Prioritization | Alignment | Other]
**Tags:** [pillar, metric, segment]
## Decision
[1-2 sentences: what was decided]
## Context
[What prompted this — the trigger]
## Alternatives Considered
1. **[Option A]** — [brief description, why not chosen]
2. **[Option B]** — [brief description, why not chosen]
## Evidence
- [Data point, customer insight, or signal that drove the call]
## Stakeholders
- **Decision maker:** [who]
- **Consulted:** [who]
- **Informed:** [who]
## Expected Outcome
[What we expect to happen, and how we'll know]
## Risk / Reversal Cost
[How hard is this to undo — low/medium/high, and why]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 90 lines · 39 tokens per session scan A cbf5fdc5fe47
decision-logger is a skill published in the GitHub repository hardiktiwari/PM-operating-OS (5 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 730 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bcc-throughline
BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.
handoff
Guides the Claude Code agent through completing a task, selecting a handoff tier, building a valid completion-card, and performing a clean task handoff.
execute-plan
Implement a written plan (from write-plan or interview-plan) when the user says execute or implement it. Loads the plan, executes ready tasks in waves in the ticket venue, runs the plan's review gate itself. Do not use while still interviewing or writing the plan.
generate-stories
Translate a single Epic into clear, actionable User Stories with explicit acceptance criteria. Activate when an Epic is defined and work needs to be prepared for Delivery execution.
review-input
Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state. Universal interceptor with domain auto-detection, 2-phase classification + evaluation, and triple-verdict output (veracity / fit / actionability). Anti-girouette guardrail…
review-story-alignment
Adversarial review of generated stories against the Discovery Session Brief, referenced DECs, and Epic DoR. Detects contradictions, omissions, and intent drift BEFORE stories reach Delivery. Produces a structured verdict (PASS/FAIL) with specific findings per story. Triggers after generate-stories, before backlog…