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/tunahanaliozturk/atelierWrote 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/tunahanaliozturk/atelier/retry)<a href="https://agentmods.dev/commands/tunahanaliozturk/atelier/retry"><img src="https://agentmods.dev/badge/commands/tunahanaliozturk/atelier/retry/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/tunahanaliozturk/atelier/retry"><img src="https://agentmods.dev/badge/commands/tunahanaliozturk/atelier/retry.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00020 | $0.00235 |
| Opus 5 | $0.00010 | $0.00118 |
| Sonnet 5 | $0.00004 | $0.00047 |
| Haiku 4.5 | $0.00002 | $0.00023 |
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 12d 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
Retry work in the most recently modified mission file under .atelier/missions/:
- Read and parse it with
parseMission(fromlib/mission.mjs). If there is no mission file, say so and stop. - Determine the targets: if
$ARGUMENTSnames a task id, that one task; otherwise every task whose status isblocked. If a named id does not exist or there are no blocked tasks, say so and stop. - For each target, reset its status to
pendingwithsetTaskStatus, append a decision-log entry recording the retry and why, and write the file back withrenderMission. - Dispatch each reset task to its assigned agent and run it through the full verify loop
(verifying-task-output: spec review, then quality review). Update the mission with the
mission-tracking skill to
doneorblockedas the outcome dictates.
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.
- 12d ago First seen · 18 lines · 20 tokens per session scan A 241279442807
retry is a command published in the GitHub repository tunahanaliozturk/atelier (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 235 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
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
app-review
Run code review on a specific branch or open PR-equivalent.
bob-work
Drain the board as a worker — claim pending tasks Claude can do, execute them, submit results.
decree
Issue a decree. Seats the organization on first use, then dispatches the teams.
bob-new
Provision a well-formed task onto the Bob board from a rough description.
report
The full account of the current decree — every figure verified before stated.