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 skills/mooqii/openpanels/myopenpanels-task-queuenpx skills add mooqii/OpenPanels --skill myopenpanels-task-queuegit clone --depth 1 https://github.com/mooqii/OpenPanelsWrote 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/skills/mooqii/openpanels/myopenpanels-task-queue)<a href="https://agentmods.dev/skills/mooqii/openpanels/myopenpanels-task-queue"><img src="https://agentmods.dev/badge/skills/mooqii/openpanels/myopenpanels-task-queue.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 | $0.00033 | $0.00567 |
| Opus 5 | $0.00016 | $0.00283 |
| Sonnet 5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
myopenpanels-task-queue 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
Use the generic Task commands returned by command catalog discovery. The tasks
table and generic Task service are authoritative; do not call queue-specific
HTTP endpoints or mutate panel state to change a Task lifecycle.
Intent routing:
- For read-only Task state and its embedded execution summaries, read
references/inspect.md. - To retry a failed Task, read
references/retry.md. - To cancel a Task, read
references/cancel.md. - To archive a terminal Task, read
references/archive.md. - For an exact Studio Task scope handoff, read
references/execute-scope.md.
- Run the exact
task handoff startselector supplied by Studio. It registers and claims on execution, not when the instruction is copied. - Follow the returned ExecutionBundle and Delivery Contract without separately loading Catalogs, Panel Skills, or portable Skills.
- Write only the declared workspace artifacts and
execution-result.json. Usetask handoff execonly for commands explicitly allowed by the Bundle; it injects the private Broker and fencing context. - Heartbeat long work through
task handoff heartbeat. Stop immediately when heartbeat or a work command returnsexecution_fenced. - Finish through
task handoff completeortask handoff fail. The Runtime validates the result, stages declared outputs, and completes the Task, and immediately returns the next Bundle when the scope can continue. - Exit only at
completeorblocked; usetask handoff stopto abandon and release active work. Do not run low-level claim, complete, fail, or release commands for a handoff.
Use task next only for read-only discovery. A runnable Task has ready: true;
a Task can be blocked by a live lease, a future retry time, exhausted executions,
or the lack of an available Agent CLI. Persistent queue execution is owned by
the Studio Worker. Manual Agents process only the supplied execution scope.
exact-task selects only the named Task. project-drain
continues independent runnable Tasks before reporting blockers.
wiki-mutation-drain processes one prerequisite or mutation Task at a time in
mutation order until the mutation queue is empty.
Never treat process exit zero as proof of success. task handoff complete
performs the Handler's domain validation. A rejected completion is a failed
execution; stop task-bound writes as soon as the execution is fenced. Use
task read when diagnosing
prerequisite propagation or retries.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 49 lines · 33 tokens per session scan A 2acd9d411862
myopenpanels-task-queue is a skill published in the GitHub repository mooqii/OpenPanels (8 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 567 once invoked, about $0.0002 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 skills, from other repositories
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…
task-record-contract
Use when creating, updating, or reading the task record for a single implementation task. Covers required task sections, no-placeholder rules, files-first task-file frontmatter, work-unit summary template, implementation artifact linkage, and safe GitHub projection posting practices. Backend projections are documented…
setup-agenticloop
Use when a maintainer or human is setting up Agentic Loop in a target project for the first time, when source document names are non-standard or ambiguous, when .agenticloop/project.md is still unconfirmed, or when a human wants to update its development-stage profile. Discovers bounded candidate project docs once…
ops_exception_desk_workflow
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents.
oncall_handoff_lookup
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents.
foreman-to-issues
Break an approved PRD into small, dependency-ordered, vertically-sliced implementation issues written as local files in the Foreman feature directory. Each issue ships a runnable acceptance check and a declared file footprint. No GitHub, no live quizzing of the user — emits files matching Foreman's issue schema with…