session-start

session-start is a command for Claude Code, OpenCode from rianvdm/product-ai-public. It costs 13 tokens per session (676 once invoked), scanned A, original, MIT.

A session context loader that reads stored corrections, stable facts, and recent work logs at the start of a session. It selects work or personal context when the request identifies an area.

In plain words
What is it for?
Use it when resuming ongoing projects or personal work that spans multiple sessions.
Why use it?
Without saved context, an agent may repeat questions or miss earlier decisions and constraints. This helps it continue work from the latest recorded state.

Command for Claude CodeOpenCode

Written for Claude Code and OpenCode: $ARGUMENTS substitution, but also installed under .opencode/.

Good fit Use it when resuming ongoing projects or personal work that spans multiple sessions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rianvdm/product-ai-public/session-start
Install

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.

Clone the repo
git clone --depth 1 https://github.com/rianvdm/product-ai-public

Made for: Claude Code, OpenCode.

Wrote 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.

agentmods badge for session-start

README.md
[![agentmods](https://agentmods.dev/badge/commands/rianvdm/product-ai-public/session-start/github.svg)](https://agentmods.dev/commands/rianvdm/product-ai-public/session-start)
Your own site
<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.

agentmods 80×15 button for session-start

Your own site · 80×15
<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>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash 35c40e752365, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.opencode/command/session-start.md · 71 lines

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, environment
  • 01-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 work
  • 01-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]

Read the full file on GitHub · 71 lines

Changes

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.

  1. yesterday First seen · 71 lines · 13 tokens per session scan A 35c40e752365

Subscribe to this mod's changes

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.