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/retrygit 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/retry)<a href="https://agentmods.dev/commands/vitalini/ebb-ai/retry"><img src="https://agentmods.dev/badge/commands/vitalini/ebb-ai/retry.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 | $0.00278 |
| Opus 5 | $0.00004 | $0.00139 |
| Sonnet 5 | $0.00002 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
retry 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
Re-dispatch a deferred ebb-ai task that previously failed. Only valid
when the task's current status is failed. A new receipt overwrites
the old.
Common failure causes worth checking before retry:
- Provider returned a transient error (529 overloaded, 5xx) — retry almost certainly works.
CarbonBudgetExceededError— the budget couldn't be met in the remaining window. Retry alone won't help; you need/ebb-ai:reschedule <id> --by <new>to extend the deadline first.- Auth error (401 / 403) — provider key is wrong or expired. Fix the key, then retry.
Arguments
$ARGUMENTS
Expected: a single task_id. If empty, list failed tasks via
check_queue_status filtering to status=failed, then ask which to
retry.
What to do
- Call the
ebb-aiMCP server'sretry_tasktool withtask_id. - Show the resulting status. If status is again
failed, surface the error string verbatim and propose a likely cause from the list above.
Examples
/ebb-ai:retry 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 · 37 lines · 8 tokens per session scan A dec043a23f2b
retry is a command published in the GitHub repository Vitalini/ebb-ai (1 stars, last pushed 24d ago), licensed Apache-2.0. It adds 8 tokens to every session and 278 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
generate-ecosystem
Generate a validated Claude Code ecosystem (orchestrator + N sub-agents + M skills + MCPs) from a brief.
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.