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.
git clone --depth 1 https://github.com/rianvdm/product-ai-publicWrote 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/commands/rianvdm/product-ai-public/session-start)<a href="https://agentmods.dev/commands/rianvdm/product-ai-public/session-start"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/session-start/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/commands/rianvdm/product-ai-public/session-start"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/session-start.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 | $0.00013 | $0.00676 |
| Opus 5 | $0.00006 | $0.00338 |
| Sonnet 5 | $0.00003 | $0.00135 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
session-start 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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Start
Load cross-session memory to establish continuity from previous work sessions.
Your Task
$ARGUMENTS
Instructions
1. Load Corrections
Read 01-context/corrections.md in full. Apply these corrections for the rest of the conversation. Do not summarize them back to the user unless asked — just internalize them.
2. Load Stable Facts
Two stable-facts files exist:
01-context/stable-facts-work.md— Amazon work state, blockers, environment01-context/stable-facts-personal.md— Personal/side-project state, decisions, environment
If the user's arguments indicate a topic area (e.g., "continue with Exponent" → work, "Discrobble work" → personal), read only the relevant file. Otherwise, read both.
This gives you the current state of all active work, recent decisions, blockers, and environment constraints. Use this as your primary orientation — it's more current and compact than the session log.
3. Load Recent Session Logs
Two session logs exist:
01-context/session-log-work.md— Amazon work01-context/session-log-personal.md— Personal/side projects (Discrobble, discogs-mcp, ListenToMore, tldl)
If the user's arguments indicate a topic area (e.g., "continue with Exponent" → work, "Discrobble work" → personal), read only the relevant log. Otherwise, read both.
Find the last 3 entries (H2 sections) from whichever log(s) you loaded. These represent the most recent substantive work sessions.
When reviewing open threads from the session log, cross-reference against stable-facts. Don't list items that are already captured as active work or blockers — only surface threads that stable-facts doesn't cover.
4. Check for Open Threads
From the recent entries and stable-facts, identify what might be relevant to today's work. Present briefly:
**Current state** (from stable-facts):
* [2-3 most relevant active work items based on recency or user's arguments]
**Recent sessions:**
* [Date] — [Topic]: [One-line summary]
* [Date] — [Topic]: [One-line summary]
* [Date] — [Topic]: [One-line summary]
**Open threads not in stable-facts:**
* [Thread from session log entry, if any that aren't already tracked]
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.
- yesterday First seen · 71 lines · 13 tokens per session scan A 35c40e752365
session-start is a command published in the GitHub repository rianvdm/product-ai-public (15 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 676 once invoked, about $0.0001 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 2026-09-09.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.