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.
git clone --depth 1 https://github.com/Marcel-Bich/marcel-bich-claude-marketplaceWrote 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/marcel-bich/marcel-bich-claude-marketplace/sandbox-promote)<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/sandbox-promote"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/sandbox-promote/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/marcel-bich/marcel-bich-claude-marketplace/sandbox-promote"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/sandbox-promote.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 | $0.00024 | $0.00570 |
| Opus 5 | $0.00012 | $0.00285 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
sandbox-promote 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 12d 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
Promote sandbox pre-work
Promote an accepted, version-worthy WIP artifact from .credo/sandbox-tmp/<slug>/ to
.credo/sandbox/<slug>/. <slug> is the sandbox-tmp folder name (argument: $1).
First invoke the sandbox skill via the Skill tool for the two-folder model, the reference
search order, and the guardrails. Then run this flow:
-
Confirm with the user (Ask). Recommend promotion only when the artifact is good enough: the pre-work answered its clarify question and is worth versioning. Ask via AskUserQuestion whether to promote
sandbox-tmp/<slug>tosandbox/<slug>. The user decides; do not promote on your own initiative. -
On YES, move the folder. Refuse to clobber an existing destination:
src=".credo/sandbox-tmp/$1" dest=".credo/sandbox/$1" [ -d "$src" ] || { echo "sandbox-promote: no such WIP folder: $src" >&2; exit 1; } [ -e "$dest" ] && { echo "sandbox-promote: refusing to clobber existing $dest" >&2; exit 1; } mkdir -p .credo/sandbox mv "$src" "$dest" -
Fix up references. Update the item's
## Sandbox pre-workpointer fromsandbox-tmp/tosandbox/; add the entry tosandbox/INDEX.md; and mark thesandbox-tmp/INDEX.mdentry as promoted (or remove it).
Notes
- This move is NOT an item status move: the folder is not under
items/[0-9]_*, so the credo-item-move guard does not apply here and does not block it. - Versioning follows the credo folder policy: in a tracked repo
.credo/sandbox/is versioned; the WIP.credo/sandbox-tmp/stays local. Only the task / build role (role-task) commits the promotion - the plan / clarify role never commits (a single index owner avoids the.git/index.lockrace). - Extraction into
docs/is a separate step the user prompts for explicitly - not part of this command.
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.
- 12d ago First seen · 50 lines · 24 tokens per session scan A c7bb1b5c3a76
sandbox-promote is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 570 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 2026-08-30.
Other commands, from other repositories
changelog
Generate a changelog entry from git commits since the last tag using conventional commit format.
deploy
Deploy application with pre/post-deploy checks.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
ship
Complete PR workflow from commit to production with validation.
ship-deployment
This file contains platform-specific deployment and validation for /ship.