claude-sdk-rs: Command for Claude Code

.claude/commands/capture.md

capture is a command for Claude Code from bredmond1019/claude-sdk-rs. It costs 0 tokens per session (2,213 once invoked), scanned C, original, Apache-2.0.

A planning-notes command that records a conversation or research session in a structured notes file. It can also create a backlog item pointing to those notes.

In plain words
What is it for?
Use it after discussing an idea or investigation, optionally adding the result to the backlog.
Why use it?
It preserves decisions and context that could otherwise be lost before a formal plan is made.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents.

This is bredmond1019/claude-sdk-rs's own configuration. It tells Claude Code how to work on claude-sdk-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-sdk-rs configures →

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/capture.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.

agentmods badge for capture

README.md
[![agentmods](https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/capture/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/capture)
Your own site
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/capture"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/capture/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 capture

Your own site · 80×15
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/capture"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/capture.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 2,213 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00000 $0.02213
Opus 5.5 $0.00000 $0.00885
Sonnet 5.5 $0.00000 $0.00443
Haiku 4.5 $0.00000 $0.00221

Measured 11d ago against content hash c54405086b5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

capture scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Constraints, related decisions, prior work, anything the next reader needs to understand the space before reading the instructions. -->
.claude/commands/capture.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capture — Scaffold a pre-plan notes file and optionally add a backlog ticket

Captures rich conversation content from a planning or research session. Creates planning/<slug>/notes.md in the current repo as a structured holding area. If the --backlog flag is provided, it calls the /backlog-ticket command to create a backlog item pointing to these notes.

Variables

$ARGUMENTS — title or free-form description of what to capture, optionally including the --backlog flag. A slug is derived from this automatically. Example: "--backlog Work email setup with instructions" Example: "notion-dashboard Notion API read-only dashboard concept"

Execution Model

Run entirely inline. Spawn no subagent. The notes file must be populated from what was actually discussed in this session — a subagent cold-starts with no memory of that conversation and can only reconstruct it from git log, which defeats the point of a capture. The main agent already holds the context.

Instructions

Step 0 — Resolve the brain root (same walk-up as /log-work)

  1. From the current working directory, walk up parent by parent looking for a brain.toml file (its first line begins # brain.toml). The directory containing it is BRAIN_ROOT.
    • If no brain.toml is found, this is a standalone repo. If --backlog is provided, /backlog-ticket will handle standalone logic. Still create the local notes file.
  2. The brain backlog path is <BRAIN_ROOT>/planning/backlog.md.

Step 1 — Parse arguments

  1. From $ARGUMENTS derive:
    • slug — kebab-case, 2–4 words (e.g. work-email, notion-dashboard)
    • title — human-readable (e.g. Work Email Setup, Notion Dashboard)
    • description — one-line summary for the frontmatter
    • repo — the current repo's slug (read from brain.toml [[repos]] entry matching this repo's path; fall back to the directory name if standalone)
    • type — feature · improvement · research · content · business · planning-session
    • keywords — 3–5 topic terms

Read the full file on GitHub · 171 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. 11d ago First seen · 171 lines · 0 tokens per session scan C c54405086b5d

Subscribe to this mod's changes

capture 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 2,213 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.

Related

capture compared with commands from other repositories

capture next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
capturebredmond1019/claude-sdk-rsCommand231mo agoApache-2.0C0Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code
convergegithub/spec-kitCommand148kyesterdayMITA35Claude Code
implementgithub/spec-kitCommand148kyesterdayMITA14Claude Code