Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/amirsoleimani/claude-stash/editgit clone --depth 1 https://github.com/AmirSoleimani/claude-stashWrote 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/amirsoleimani/claude-stash/edit)<a href="https://agentmods.dev/commands/amirsoleimani/claude-stash/edit"><img src="https://agentmods.dev/badge/commands/amirsoleimani/claude-stash/edit.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00564 |
| Opus 5 | $0.00009 | $0.00282 |
| Sonnet 5 | $0.00003 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
edit 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 6d 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
Edit a stash item in .claude/stash.md. Two modes depending on $ARGUMENTS:
Mode A — Inline replacement (when text is provided after N):
If $ARGUMENTS is N <new text>, replace the item's text inline.
- Read
.claude/stash.md. If empty or missing, respond:Stash is empty.and stop. - Find item at position
N. If out of range, respond with the current count and stop. - Parse the line's
[YYYY-MM-DD HH:MM]prefix and keep it unchanged — the timestamp records original capture, not last edit. - Replace the line with:
Position stays the same. Other lines untouched. Save.- [<original timestamp>] <new text> - Respond:
Edited item N. N. <new text>
Mode B — Open in editor (when only N is provided, no text):
If $ARGUMENTS is just N (a positive integer with no text after it), open the file in the user's editor so they can edit any line freely.
-
Run this bash command (do not modify the file yourself):
${EDITOR:-vi} +<N+H> .claude/stash.mdWhere
<N+H>calculates the line number of item N in the file (header is typically 2 lines:# Stash+ blank line, so item N is on line N+2 — but verify by reading the file structure first). The+LINEsyntax positions the cursor on that line for most editors. -
After the editor exits, respond:
Editor closed. Run /stash:list to verify the change.
Mode C — Error (no valid input):
If $ARGUMENTS is empty or doesn't start with a positive integer, respond:
Usage:
/stash:edit N <new text> — replace inline
/stash:edit N — open in editor
Notes:
- Mode A is fastest when you know the full new text.
- Mode B is best when you want to tweak a single word, fix typos, or edit multiple lines.
- Neither mode logs to
.claude/stash.log.md. The log only tracks items leaving the stash (popped or dropped). - Timestamp preservation: if you want to refresh the timestamp (signal renewed urgency), use
/stash:drop Nthen/stash:push <text>.
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.
- 6d ago First seen · 54 lines · 17 tokens per session scan A d18d727c1d09
edit is a command published in the GitHub repository AmirSoleimani/claude-stash (10 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 564 once invoked, about $0.0001 per session on Opus 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
convert-to-todowrite-tasklist-prompt
Purpose: Transform verbose, context-heavy slash commands into efficient TodoWrite tasklist-based methods with parallel subagent execution for 60-70% speed improvements.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
cleanproject
I'll help clean up development artifacts while preserving your working code.
context-stats
Display context window usage and token statistics.
help
Explain Ralph Wiggum technique and available commands.
dashboard-session-abort-all
Abort multiple running sessions (asks which). Usage /dashboard:session-abort-all.