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/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-budget-approve)<a href="https://agentmods.dev/commands/open-latch/latch/latch-budget-approve"><img src="https://agentmods.dev/badge/commands/open-latch/latch/latch-budget-approve.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 | $0.00015 | $0.00294 |
| Opus 5 | $0.00008 | $0.00147 |
| Sonnet 5 | $0.00003 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
latch-budget-approve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
The KB auto-tooling has two daily caps as a backstop against runaway hook loops:
- 100 non-heal calls/day — compactor, latch_gate, tree summarization, on-insert heal arbitration.
- 50 heal calls/day — nightly heal LLM arbitration only.
When either cap is hit, the matching path no-ops (compactor returns
budget_cap, heal falls back to keep_both, etc.) until UTC rollover.
This command unlocks BOTH categories for the remainder of today.
Only run this when the user has explicitly asked for it. The caps exist for cost safety — do not approve on your own initiative.
Run with the Bash tool:
python "<KB_HOME>/src/latch/gate/budget.py" approve "$(pwd)"
Report back the current state from the command's JSON output (date,
count_nonheal, count_heal, approved_dates). After approval:
- Both counters reset to 0
- Today's date is added to
approved_dates - Further LLM calls in either category bypass the caps until UTC rollover
- Tomorrow's UTC day returns to normal cap behaviour
To see the current budget state without approving, run:
python "<KB_HOME>/src/latch/gate/budget.py" status "$(pwd)"
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 Changed 423053f69292
- 8d ago First seen · 37 lines · 15 tokens per session scan A 1cf8b8edb9c1
latch-budget-approve is a command published in the GitHub repository open-latch/latch (9 stars, last pushed 5d ago), licensed Apache-2.0. It adds 15 tokens to every session and 294 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
ctx
Search agent history or trace code to its original agent session.
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.
krimto-status
Show the current state of Krimto memory — total facts, scope breakdown, recent writes, and index health.
checklist
Generate a custom checklist for the current feature based on user requirements.