Borrowing it
Nothing to install: this file belongs to Haroon-jay/wctx. 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/Haroon-jay/wctx/main/.claude/commands/capture.mdgit clone --depth 1 https://github.com/Haroon-jay/wctxWrote 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/haroon-jay/wctx/capture)<a href="https://agentmods.dev/commands/haroon-jay/wctx/capture"><img src="https://agentmods.dev/badge/commands/haroon-jay/wctx/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/haroon-jay/wctx/capture"><img src="https://agentmods.dev/badge/commands/haroon-jay/wctx/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 | $0.00016 | $0.00332 |
| Opus 5.5 | $0.00006 | $0.00133 |
| Sonnet 5.5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
capture 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 2mo 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.
What it actually says
Record this session's findings using the finalize_session MCP tool from wctx.
Pass your own session id as sessionId — it is imported automatically if wctx has not seen it yet.
Include only what is worth keeping. Judge that yourself; you know which of this session's facts were hard-won and which were routine:
- a root cause, especially one that turns out to live in a different repository than the symptom
- a decision with a rationale that would not be obvious from reading the diff
- a constraint discovered the hard way — a rate limit, an ordering requirement, a rejected approach
- a question left unresolved, together with what was ruled out
- a surprise: behaviour that contradicted the code's apparent intent
For each item set repository to the repository the finding is about (often not the one being
edited) and attach the files and symbols it concerns, with line numbers where you know them. That
provenance is what makes the finding verifiable and retrievable later.
Prefer specific, falsifiable statements. "The SDK returns 419 as terminal with no retry" is worth keeping; "error handling could be improved" is not. Skip routine work, anything already obvious from the code, and anything that will be stale within a day.
If nothing meets that bar, say so plainly and record nothing rather than padding the store.
Then tell me, in two lines, what you recorded and what you deliberately left out.
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.
- 2mo ago First seen · 29 lines · 16 tokens per session scan A 1aa291ca5946
capture is a command published in the GitHub repository Haroon-jay/wctx (7 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 332 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
end
End a session — log what happened and propose durable memory updates.
dream
Run a curator pass over the memory dir. Produces a proposal artifact for /dream-apply. Default curator: rot.
start
Start a session — load context + memory and brief yourself on current state.
update
Mid-session checkpoint — save progress without ending the session.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.