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/capture.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/capture)<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.
<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>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 | $0.02213 |
| Opus 5.5 | $0.00000 | $0.00885 |
| Sonnet 5.5 | $0.00000 | $0.00443 |
| Haiku 4.5 | $0.00000 | $0.00221 |
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. --> 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)
- From the current working directory, walk up parent by parent looking for a
brain.tomlfile (its first line begins# brain.toml). The directory containing it isBRAIN_ROOT.- If no
brain.tomlis found, this is a standalone repo. If--backlogis provided,/backlog-ticketwill handle standalone logic. Still create the local notes file.
- If no
- The brain backlog path is
<BRAIN_ROOT>/planning/backlog.md.
Step 1 — Parse arguments
- 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
- slug — kebab-case, 2–4 words (e.g.
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 · 171 lines · 0 tokens per session scan C c54405086b5d
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.
capture compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| capturebredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | C | 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 |