Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add synaptiai/synapti-marketplace/plugin install thanosWrote 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/synaptiai/synapti-marketplace/snap)<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/snap"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/snap/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/synaptiai/synapti-marketplace/snap"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/snap.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 | $0.00029 | $0.00908 |
| Opus 5.5 | $0.00012 | $0.00363 |
| Sonnet 5.5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
snap scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/snap
Review mode. This command works out what to review, hands it to the
thanos subagent, and shows its review. It never edits files and never
applies a suggestion; acting on a review is a separate request from the
user.
The argument is the text Claude Code appends after ARGUMENTS: at the
end of this command; with no such line, the argument is empty. This file
never places the argument anywhere itself, so nothing in it is run as
shell when the command loads.
Default target
The block below resolves the target for an empty argument.
"${CLAUDE_PLUGIN_ROOT}/bin/snap-target.sh"
Steps
- Pick the target output.
- If the argument is empty, use the block's output.
- Otherwise run the script yourself with the Bash tool, passing the
argument as one single-quoted word, and use that output instead.
The command is exactly the
THANOS_SCRIPTpath from the block in single quotes, a space, and the argument in single quotes, with each'inside the path or the argument written as'\''. For an argumenta'bthat is'<THANOS_SCRIPT>' 'a'\''b'. Nothing else goes in that command: no pipes, no;, no second command, and no other way of passing the argument.
- Check the output before using it. It must have exactly one
THANOS_TARGET=line, and every line must start with one ofTHANOS_SCRIPT=,THANOS_TARGET=,THANOS_WHAT=,THANOS_READ=,THANOS_UNTRACKED=orTHANOS_NOTHING=. Unless the target isnone, it must have exactly oneTHANOS_READ=line, and its value must begit diff <id>,git diff <id> <id>orgit show <id>with each<id>40 or 64 hexadecimal characters, or a path starting with/. EveryTHANOS_UNTRACKED=value must also start with/. If any of this fails, say the target could not be resolved, show the first line of the output, and stop. Do not invoke the subagent. - If it printed
THANOS_TARGET=none, reply with theTHANOS_NOTHINGtext as a single line and stop. Do not invoke the subagent. - Otherwise invoke the
thanossubagent with the Agent tool. Pass this prompt, filled in from the output:
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.
- 4d ago First seen · 76 lines · 29 tokens per session scan A ca97086fe8fe
snap is a command published in the GitHub repository synaptiai/synapti-marketplace (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 29 tokens to every session and 908 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 2026-10-16.
Other commands, from other repositories
create-worktree
Follow these steps to create a git worktree.
production-upgrade
Run the full product upgrade pipeline — 55-agent iterative review with CEO/Engineering/UX/QA parallel loops.
review
Pre-landing code review — analyzes diff for SQL safety, LLM trust boundaries, conditional side effects, missing tests, dependency risks, and security issues.
review
Run code-review and security-review skills against the current diff. Safe to run repeatedly during Build.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.