A command that marks one planned work block as in progress in status.md, or chooses the first unfinished block when no identifier is given.

Use it to start the next eligible block or a named block after checking that earlier blocks are complete.

It keeps the project status and current focus aligned while preventing work from skipping unfinished prerequisites.

How bredmond1019/claude-sdk-rs configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/start-block.md

Clone the repo

git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/start-block/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/start-block)

Your own site

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/start-block"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/start-block/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/start-block"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/start-block.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 721 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00721
Opus 5.5	$0.00000	$0.00288
Sonnet 5.5	$0.00000	$0.00144
Haiku 4.5	$0.00000	$0.00072

Measured 11d ago against content hash 99800cfe0578, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

start-block 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.

.claude/commands/start-block.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start Block — Mark a block as in-progress in status.md.

Variables

$ARGUMENTS — optional block identifier to start (e.g. <spec-slug>). If omitted, defaults to the first block that is not Done in status.md.

Execution Model

Run entirely inline. Spawn no subagent. This is a small status.md/state.json edit — a subagent round trip adds latency without adding value.

Instructions

Read planning/status.md.
Identify the target block:
- If $ARGUMENTS is provided, find that block by identifier. If not found, say so and stop.
- If $ARGUMENTS is omitted, find the first block that is not Done.
Check preconditions:
- If the block is already In progress, report that and stop.
- If the block is Done, report that and stop.
- If any block that must precede this one (all blocks above it in the sequence) is not Done, report which ones are incomplete and stop — do not skip the sequence.
Update the block's status to In progress in status.md. Preserve all other content and formatting.
Update the Current focus line to reflect this block.
Bump the Last updated date.
Write the updated status.md.
Flip the matching block's status in planning/state.json, if the repo has one. status.md and state.json both name the same block — a /start-block that touches only status.md leaves the authoritative graph stale. Resolve the target block's canonical ID (the <BlockID> in status.md's row, or the id it maps to in state.json's tracks[].blocks[] if status.md only carries a bare letter) and:
- Find that block in tracks[].blocks[] (search every track). If it does not exist, report that and stop — do not fabricate a new block entry here (that's /generate-master-plan//plan//chore/ /ticket's job).
- Set its status to "in_progress" (an authored value — never hand-set "blocked", see docs/state/state-schema.md).
- Save planning/state.json and validate it is still valid JSON: python3 -c "import json;json.load(open('planning/state.json'))". This is a parse-only sanity check, not schema validation — it cannot catch a shape mismatch (e.g. a struct-typed field like origin written as a scalar), which parses fine as JSON and only fails mev's typed deserialization. For real schema confidence, run mev validate-brain --state.
- Run mev emit-state --write to refresh focus.now/focus.next from the new status.

Read the full file on GitHub · 55 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.

11d ago First seen · 55 lines · 0 tokens per session scan A 99800cfe0578

Subscribe to this mod's changes

start-block is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 721 tokens. 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.

Planning Project management

start-block next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
start-blockbredmond1019/claude-sdk-rs	Command	23	1mo ago	Apache-2.0	A	0	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

claude-sdk-rs: Command for Claude Code