Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/begin-session.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/bredmond1019/claude-sdk-rs/begin-session)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/begin-session"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/begin-session/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/bredmond1019/claude-sdk-rs/begin-session"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/begin-session.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 | $0.00059 | $0.01740 |
| Opus 5.5 | $0.00024 | $0.00696 |
| Sonnet 5.5 | $0.00012 | $0.00348 |
| Haiku 4.5 | $0.00006 | $0.00174 |
Grade A, and why
begin-session 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Begin Session — one bounded piece of operator work, start to finish
/orchestrate drives work an agent can do alone. /begin-session drives work it cannot — the
decision, the credential, the judgement call, the thing only the operator can answer.
The failure this exists to prevent is measured, not theoretical. A Dev.to sweep whose dry-run was four identical one-line diffs — fifteen seconds of review — sat unactioned for days because the decision lived in a markdown file nobody opens. The tooling was finished. The gate was a document.
So a session is not a reminder and not a backlog row. It is a sitting, with:
- a repo you run it from (and, when relevant, a machine),
- an exit artifact — the thing that exists afterwards and did not before,
- and an ending. A session that does not produce its artifact did not happen.
Variables
$ARGUMENTS — the session slug, optionally with flags.
Usage: /begin-session <session-slug> [--roadmap <path>] [--dry-run]
| Flag | Default | What it does |
|---|---|---|
<session-slug> |
required | e.g. operator-developer-offer. Kebab-case, prefixed operator-. |
--roadmap <path> |
inferred | Where the session is defined, when it is not yet a graph edge. |
--dry-run |
off | Print the resolved session, its exit artifact and gated blocks; change nothing. |
Empty $ARGUMENTS → print usage, list every session you can resolve, and stop.
Step 1 — Resolve the session
Look in this order and stop at the first hit:
planning/state.jsondepends_onedges of typeoperatorcarrying this slug — the real home now thatokf-core:OK.ticket.operator-edge-typeshas landed ({"type":"session"}is a hard parse error). Collect every block gated by it, across every repo: one session commonly gates several, and the operator should see all of them.- A roadmap's Wave 0 session table (
--roadmap, or searchplanning/*/roadmap.md) — where sessions live before the edge type exists. planning/<slug>/notes.md— a/captureholding area.
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 · 129 lines · 59 tokens per session scan A 07d7c910cbb6
begin-session is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,740 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 2026-10-26.
begin-session compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| begin-sessionbredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 59 | Claude Code |
| wsdanielmiessler/LifeOS | Command | 20k | yesterday | MIT | A | 0 | Claude Code |
| cancel-ralphanthropics/claude-plugins-official | Command | 46k | yesterday | Apache-2.0 | A | 4 | Claude Code |
| engage.actionshypnguyen1209/offensive-claude | Command | 412 | 15d ago | MIT | A | 11 | Claude Code |
| focusData-Wise/claude-plugins | Command | 7 | yesterday | MIT | A | 0 | Claude Code |
| stuckData-Wise/claude-plugins | Command | 7 | yesterday | MIT | A | 0 | Claude Code |
| quickstartorq-ai/assistant-plugins | Command | 6 | 2d ago | MIT | A | 23 | Claude Code |