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/desplega-ai/agent-swarmWrote 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/desplega-ai/agent-swarm/review-offered-task)<a href="https://agentmods.dev/commands/desplega-ai/agent-swarm/review-offered-task"><img src="https://agentmods.dev/badge/commands/desplega-ai/agent-swarm/review-offered-task/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/desplega-ai/agent-swarm/review-offered-task"><img src="https://agentmods.dev/badge/commands/desplega-ai/agent-swarm/review-offered-task.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 | $0.00017 | $0.00451 |
| Opus 5 | $0.00009 | $0.00226 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
review-offered-task 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 10d 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
Review Offered Task
You have been offered a task. Your job is to review it and decide whether to accept or reject it based on your capabilities and current workload.
Workflow
-
Get task details: Call the
get-task-detailstool with the providedtaskIdto understand what the task involves. -
Evaluate the task: Consider:
- Does this task match your capabilities?
- Do you have the necessary context or access to complete it?
- Is the task description clear enough to proceed?
-
Make a decision:
- Accept: If you can complete this task, call
task-actionwithaction: "accept"andtaskId: "<taskId>". Then immediately use/work-on-task <taskId>to start working on it. - Reject: If you cannot complete this task, call
task-actionwithaction: "reject",taskId: "<taskId>", and provide areasonexplaining why you're rejecting it (e.g., "Task requires Python expertise which I don't have", "Task description is too vague").
- Accept: If you can complete this task, call
Example Accept Flow
1. get-task-details taskId="abc-123"
2. [Review the task details]
3. task-action action="accept" taskId="abc-123"
4. /work-on-task abc-123
Example Reject Flow
1. get-task-details taskId="abc-123"
2. [Review the task details]
3. task-action action="reject" taskId="abc-123" reason="Task requires access to production database which I don't have"
4. Reply "DONE" to end the session
Important Notes
- Always provide a clear reason when rejecting a task - this helps the lead agent reassign it appropriately
- If you accept, you must immediately start working on the task using
/work-on-task - If you reject, the task returns to the unassigned pool for reassignment
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.
- 10d ago First seen · 46 lines · 17 tokens per session scan A 155bf08553c9
review-offered-task is a command published in the GitHub repository desplega-ai/agent-swarm (758 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 451 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 2026-08-30.
Other commands, from other repositories
distill
Distill repository files into the RLM Summary Ledger using agentic intelligence (fast) or Swarm Workers (offline batch).
distill-agent
High-speed RLM distillation of project documentation using agentic intelligence.
os-loop
Run a full OS improvement cycle — execute, eval, emit friction events, close with post-run metrics, and trigger a Triple-Loop Retrospective if the friction threshold is crossed.
os-init
Bootstrap the project by triggering the agentic-os-setup conversational architect.
os-memory
Force garbage collection and conflict resolution on the tiered memory system.
os-architect
Front-door intake for Agentic OS evolution — classifies intent, audits existing capabilities, proposes a path (A/B/C), and dispatches implementation work via Copilot CLI.