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/vitalini/ebb-ai/expeditegit clone --depth 1 https://github.com/Vitalini/ebb-aiWrote 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/vitalini/ebb-ai/expedite)<a href="https://agentmods.dev/commands/vitalini/ebb-ai/expedite"><img src="https://agentmods.dev/badge/commands/vitalini/ebb-ai/expedite.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 | $0.00013 | $0.00431 |
| Opus 5 | $0.00006 | $0.00216 |
| Sonnet 5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
expedite 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 5d 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
Run a deferred ebb-ai task right now instead of waiting for the cleanest
grid window the scheduler picked. The resulting receipt is tagged
intensitySource=expedited so it's clear the dispatch decision was
caller-overridden rather than scheduler-chosen.
Use this when:
- The user changed their mind and wants the result before the deadline.
- An upstream dependency landed early and downstream work is blocked.
- You're debugging a task and want to see it run end-to-end.
Do not use this just because the user is impatient — the whole
point of /ebb-ai:defer is to defer. If they want sync calls, they
shouldn't have deferred.
Arguments
$ARGUMENTS
Expected: a single task_id. If empty, list candidates first via
check_queue_status and ask which to expedite.
What to do
- Call the
ebb-aiMCP server'sexpedite_tasktool withtask_id. - Report the resulting status and any error (that is all the tool
returns:
statusplus anerrorline on failure). - To show the user the actual LLM response and the carbon receipt, follow
up with
/ebb-ai:check <task_id>— the detail view carries theResult:block once the dispatch completed. - Remind the user that this dispatch bypassed the carbon-aware window —
the receipt's
intensity_sourcewill readexpedited.
If the tool fails with "no provider API key set", tell the user that
expedite requires ANTHROPIC_API_KEY (or OPENAI_API_KEY) in the MCP
server's env config — and that without a key, the only path is to wait
for the ebb tick daemon (if configured) to dispatch normally.
Examples
/ebb-ai:expedite 7f3a2b9e
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.
- 5d ago First seen · 47 lines · 13 tokens per session scan A e3de8b2eb735
expedite is a command published in the GitHub repository Vitalini/ebb-ai (1 stars, last pushed 25d ago), licensed Apache-2.0. It adds 13 tokens to every session and 431 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
escribe-dialogo
Generates short dramatic-comedy dialogue stories between a fixed astronaut and a robot assistant from a user prompt, saved as a Markdown file. Use when the user invokes /escribe-dialogo or asks to write a space dialogue, relato, or historia with two characters.
gov-reuse
Discover reusable UK government code before building from scratch.
repo-docs
Generate and maintain agent-readable repository documentation from source, docs, and git history.
review-pr
Reviews pull requests with three independent checkers (security, performance, tests) and aggregates findings into a single structured comment. Use when the user says "review PR", "audit diff", or "ship this", or whenever a GitHub PR URL is pasted. Does NOT modify code — it only reports findings.
add-tool
Add a new MCP tool to server.py.
add-adapter-method
Add a new method to both Airflow adapters.