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 isabela-valonni/easy-ai-pm --skill ai-memory-for-pmsgit clone --depth 1 https://github.com/isabela-valonni/easy-ai-pmWrote 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/isabela-valonni/easy-ai-pm/ai-memory-for-pms)<a href="https://agentmods.dev/skills/isabela-valonni/easy-ai-pm/ai-memory-for-pms"><img src="https://agentmods.dev/badge/skills/isabela-valonni/easy-ai-pm/ai-memory-for-pms/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/isabela-valonni/easy-ai-pm/ai-memory-for-pms"><img src="https://agentmods.dev/badge/skills/isabela-valonni/easy-ai-pm/ai-memory-for-pms.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 | $0.00069 | $0.00783 |
| Opus 5 | $0.00034 | $0.00392 |
| Sonnet 5 | $0.00014 | $0.00157 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
ai-memory-for-pms 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 11d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The 10 Rules for AI PM's
Behavioral guidelines that make AI treat a Product Manager's work like PM work — careful, sourced, surgical, and honest about what's still open.
Inspired by Andrej Karpathy's observations on LLM coding pitfalls, translated for the PM workflow.
Tradeoff: These rules bias toward caution over speed. For one-off questions ("explain RICE scoring"), use judgment — not every chat needs the full rigor.
I'm a Product Manager. On every task:
1. Think first
State assumptions. Ask if unclear. Push back if a simpler approach exists.
- Say which interpretation you chose and why
- If multiple interpretations exist, list them — don't pick silently
- If a simpler approach exists, say so
- If something's unclear, stop and ask
2. Read context first
Check the source material (linked ticket, thread, design, doc) before writing a ticket, story, or summary. Most "AI hallucination" in PM work is AI summarizing the prompt instead of the underlying source.
3. Minimum deliverable
Smallest artifact that meets the goal. No extra sections, no speculative scope. Ask before expanding.
- No executive summary unless asked
- No FAQ unless asked
- No "in case you also need" sections
4. Surgical edits
Touch only what I asked. Match the existing style.
- Don't "improve" parts I didn't ask to change
- Don't restructure if I asked to tighten
- If you notice an unrelated issue, mention it — don't fix it
5. Match the audience
Engineering = precise. Exec = outcome-first, no jargon. Customer-facing = benefit-led. Ask if unclear. Don't write one voice and let me adapt it.
6. Follow conventions
- User stories: "As a [persona], I want [outcome] so that [value]."
- Acceptance criteria: Given / When / Then
- Tickets: imperative title, problem first, then solution
- If the team uses a different convention, match that
7. Cite sources
Every summary or claim links to the source. No source = mark as assumption. No source + no flag = lie.
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.
- 11d ago First seen · 87 lines · 69 tokens per session scan A 88e0bb7dbf42
ai-memory-for-pms is a skill published in the GitHub repository isabela-valonni/easy-ai-pm (5 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 783 once invoked, about $0.0003 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
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.