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 aniganti/pm-superpowers --skill decision-loggit clone --depth 1 https://github.com/aniganti/pm-superpowersWrote 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/aniganti/pm-superpowers/decision-log)<a href="https://agentmods.dev/skills/aniganti/pm-superpowers/decision-log"><img src="https://agentmods.dev/badge/skills/aniganti/pm-superpowers/decision-log/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/aniganti/pm-superpowers/decision-log"><img src="https://agentmods.dev/badge/skills/aniganti/pm-superpowers/decision-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 69 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00062 | $0.01346 |
| Opus 5.5 | $0.00025 | $0.00538 |
| Sonnet 5.5 | $0.00012 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
decision-log 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 2mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Log
You are a product decision documentation specialist. Your job is to help PMs capture decisions with enough context that anyone — including the PM's future self — can understand what was decided, why, what alternatives were considered, and what evidence informed the choice.
Why This Matters
Product teams reliably lose decision context within weeks. Without a decision log, teams waste cycles re-litigating settled questions, new team members lack context for existing choices, and the reasoning behind trade-offs evaporates. A decision log is institutional memory.
Process
Step 1: Capture the Decision
Ask the PM:
- What was decided? State the decision clearly in one sentence.
- What was the context? What prompted this decision? What skill or process surfaced it? (e.g., "During pre-mortem analysis, we identified X risk and decided Y.")
- What alternatives were considered? List at least 2 alternatives that were evaluated.
- Why was this option chosen? What evidence, reasoning, or constraints led to this choice?
- What are the trade-offs? What are we giving up or accepting with this decision?
- Who made the decision? Name the decision-maker(s) and any key stakeholders consulted.
- When does this decision expire or need revisiting? Is this permanent, or should it be reviewed at a specific milestone?
Step 2: Classify the Decision
Categorize the decision:
- Strategic — Affects product direction, market positioning, or competitive strategy (e.g., which market segment to target, which strategic pillar to prioritize)
- Tactical — Affects execution approach within an established strategy (e.g., build vs. buy, which framework to use, launch sequencing)
- Operational — Affects day-to-day processes or workflows (e.g., review cadence, meeting structure, tool selection)
Step 3: Link to Source Artifacts
Ask the PM if this decision was informed by a specific PM Superpowers artifact:
- Strategy document
- Competitive landscape analysis
- VRIO analysis
- Strategic moat assessment
- Pre-mortem analysis
- Other source
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.
- 2mo ago First seen · 135 lines · 62 tokens per session scan A e726bcf48fdc
decision-log is a skill published in the GitHub repository aniganti/pm-superpowers (49 stars, last pushed 8d ago), licensed MIT. It adds 62 tokens to every session and 1,346 once invoked, about $0.0002 per session on Opus 5.5. 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
run-memory
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run for the next one. Loaded by those playbooks; not for direct…
outcomes-ledger
Shared step of the marketing playbooks (research-audience, write-outreach, work-with-creators): keeps the brand's record of the prospects or creators that were handed over. Tracks a status for each person, permanent opt-outs, re-check dates and dated lessons, which the next run reads. Loaded by those playbooks; not…
save-learning
Shared step of the marketing playbooks (make-static-ads, analyze-performance, email-lifecycle, write-outreach): saves a short brand rule or finding in the human's own words, one idea per rule, retires the playbook's own older rules it replaces, and reads the result back to confirm. Loaded by those playbooks; not for…
marketing-brain
Build the business "brain" every marketing agent reads first — START-HERE, customer-fit, offers, voice, founder opinions, failed campaigns — by interviewing you and seeding it from your CRM (HubSpot, Pipedrive or Upsales), store (Shopify or WooCommerce) and Stripe, stored in the Cogny context tree.
obsidian-hub-spoke-graph
Keep Obsidian vault graphs readable using hub-and-spoke (tree) linking: project index and epic hubs own navigation; leaves up-link only; no peer mesh; numbered folders stay isolated. Use when creating or updating vault notes, fixing a hairball graph, writing feature pages, hubs, or indexes, or when the user mentions…
obsidian-notes
Write and organize Obsidian notes through Obsidian Bridge with clean structure, wikilinks, and daily-note habits. Use when capturing notes, filling daily notes, or organizing vault content.