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 skills/open-latch/latch/source-command-latch-gatenpx skills add open-latch/latch --skill source-command-latch-gategit clone --depth 1 https://github.com/open-latch/latchWhat 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 | $0.00059 | $0.00716 |
| Opus 5 | $0.00030 | $0.00358 |
| Sonnet 5 | $0.00012 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
source-command-latch-gate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
source-command-latch-gate
Use this skill when the user explicitly asks to run latch gate as a manual second opinion on a request or implementation plan.
Command Template
If the user did not provide a request, ask for the request to gate. Prefer the
Codex MCP latch_gate/kb_gate tool when it is available. If you use the shell
fallback, explicitly substitute the user's request text; Codex does not populate
Claude slash-command argument placeholders.
latch_home="${LATCH_HOME:-}"
if [ -z "$latch_home" ] && [ -n "${CLAUDE_KB_HOME:-}" ]; then
latch_home="$CLAUDE_KB_HOME"
fi
if [ -z "$latch_home" ]; then
search_dir="$PWD"
while [ "$search_dir" != "/" ]; do
if [ -f "$search_dir/AGENTS.md" ]; then
latch_home="$(sed -n 's|.*Follow `\([^`]*\)/README\.md` per-user setup.*|\1|p' "$search_dir/AGENTS.md" | head -n 1)"
[ -n "$latch_home" ] && break
fi
search_dir="$(dirname "$search_dir")"
done
fi
if [ -z "$latch_home" ]; then
candidate="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
if [ -f "$candidate/src/mcp_server.py" ] && [ -d "$candidate/commands" ]; then
latch_home="$candidate"
fi
fi
if [ -z "$latch_home" ] || [ ! -f "$latch_home/src/mcp_server.py" ]; then
echo "Could not find latch checkout; set LATCH_HOME to your latch install." >&2
exit 1
fi
request="$(cat <<'EOF'
<exact user-provided request to gate>
EOF
)"
if [ -z "${LATCH_GATE_BACKEND:-}" ] && [ -z "${CLAUDE_KB_GATE_BACKEND:-}" ] && [ -z "${LATCH_MODEL_BACKEND:-}" ]; then
export LATCH_GATE_BACKEND=codex
fi
bash "$latch_home/bin/run_latch_gate.sh" "$request"
After the command returns, show an explicit Latch gate block. Prefer the
returned findings object when present. If the result says latch is UNLATCHED,
report that latch gate was skipped, do not claim KB evidence was read, and tell
the user to run /unlatch to re-latch. Otherwise, lead with provenance, then
include the recommendation, summary/rationale, receipt or source basis, cited
evidence nodes with status/current authority, any better next action, and
uncovered claims.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 64 lines · 59 tokens per session scan A e63c558a9e0d
source-command-latch-gate is a skill published in the GitHub repository open-latch/latch (9 stars, last pushed 3d ago), licensed Apache-2.0. It adds 59 tokens to every session and 716 once invoked, about $0.0003 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 skills, from other repositories
weave
Parallel strand orchestration — decompose a task into 3+ independently scoped strands, fan out real subagents (worktree-isolated when they write files), and coordinate through a session file and Insight Capsules. Use ONLY when the user explicitly invokes it by name or slash command.
agentbro-release
Use when releasing AgentBro from this repository: merging dev/main, bumping versions, updating release notes, tagging, pushing, monitoring GitHub Actions, Homebrew cask publication, or fixing a bad release.
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
agentbro-pr-merge
Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.
mcp-media-inbox-triage
Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.
mcp-sheet-cache-bridge
Keep Zapier Tables or another MCP-connected record store as the source of truth while Google Sheets-based tools read an event-driven cache tab.