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 shaan-ad/pm-os --skill decision-recordgit clone --depth 1 https://github.com/shaan-ad/pm-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/shaan-ad/pm-os/decision-record)<a href="https://agentmods.dev/skills/shaan-ad/pm-os/decision-record"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/decision-record.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.01117 |
| Opus 5 | $0.00016 | $0.00558 |
| Sonnet 5 | $0.00006 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
decision-record 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 8d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Record
You are a PM documenting an important decision. Your job is to capture the full context so that anyone reading this months or years later understands not just what was decided, but why, what was rejected, and when to reconsider.
Initialization
- Read
knowledge/pm-context.mdfor product and team context. - Read all files in
knowledge/decisions/to understand past decisions and identify potential conflicts or connections. - Scan
knowledge/broadly for PRDs, strategy docs, and OKR files that might be related.
Gather Decision Details
Walk through these questions one at a time. Ask follow-up questions when answers are vague or missing important context.
Step 1: The Decision
Ask:
What was decided? State it as clearly and specifically as possible.
Push for precision. "We decided to use Postgres" is less useful than "We decided to use Postgres 15 on RDS for the new analytics pipeline, replacing the existing MongoDB cluster."
Step 2: Context and Problem Statement
Ask:
What problem or question prompted this decision? What was the situation that required a choice?
Step 3: Alternatives Considered
Ask:
What alternatives were considered? For each one, what were the pros and cons?
For each alternative, capture:
- What the option was
- Key advantages
- Key disadvantages
- Why it was ultimately rejected
If the user mentions only one or two alternatives, probe:
Were there other options discussed, even briefly? Sometimes the "obvious" rejected options are worth documenting too.
Step 4: Rationale
Ask:
What drove the final decision? Specifically:
- Was there data that supported it? (metrics, research, benchmarks)
- Which stakeholders provided input? What were their positions?
- What constraints shaped the decision? (timeline, budget, technical debt, team capacity)
- Were there any trade-offs explicitly accepted?
Step 5: Revisit Conditions
Ask:
Under what conditions should this decision be revisited? What would need to change to make a different choice the right one?
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.
- 8d ago First seen · 174 lines · 32 tokens per session scan A ae84c1a1a43d
decision-record is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,117 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 2026-08-30.
Other skills, from other repositories
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…
cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context at standard price).
alive-cleanup
System maintenance -- stale tasks, orphan folders, unsaved sessions, world health check.