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/open-latch/latch/latch-gate-reportgit clone --depth 1 https://github.com/open-latch/latchWrote 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/open-latch/latch/latch-gate-report)<a href="https://agentmods.dev/commands/open-latch/latch/latch-gate-report"><img src="https://agentmods.dev/badge/commands/open-latch/latch/latch-gate-report.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 | $0.00008 | $0.00218 |
| Opus 5 | $0.00004 | $0.00109 |
| Sonnet 5 | $0.00002 | $0.00044 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
latch-gate-report 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.
What it actually says
Show a read-only, friendly proof receipt over recent latch_gate activity. This
command summarizes structural logs only: gate verdicts, outcome rows, adversary
deltas, explicit decision signals, top cited KB node ids/status, priority
evidence, and uncovered-claim/gap counts.
It does not run a new gate, does not read raw prompt text or KB bodies from the logs, and does not write decisions. Treat it as a compact value report for how latch has been applying project judgment recently, not as analytics/RL/dashboarding.
Run
bash <KB_HOME>/bin/latch_gate_report.sh $ARGUMENTS
After the command returns, show the report as-is. If the user asks for a cited
node body, fetch that node with latch_get(<id>) separately.
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 · 24 lines · 8 tokens per session scan A bb379ec754b8
latch-gate-report is a command published in the GitHub repository open-latch/latch (9 stars, last pushed today), licensed Apache-2.0. It adds 8 tokens to every session and 218 once invoked, about $0.0000 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
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
handoff-export
Read .claude/skills/handoff/SKILL.md completely and dispatch its export workflow. Use any supplied command arguments only as the requested bundle path; preserve the skill's sourceagent, direct checks, optional verification, and safety boundaries.
handoff
Export a Waybill Bundle by default, or import one when requested.
waybill
Alias that exports by default or imports when requested.
make-this
Install the Multi-Agent Loop Kit into the current repo and run the setup interview.
listen
Show what a given agent should read before coding, plus briefs/approvals mentioning it.