Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HelixDevelopment/codenpx agentmods add skills/helixdevelopment/code/scheduled-work-queueWrote 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/helixdevelopment/code/scheduled-work-queue)<a href="https://agentmods.dev/skills/helixdevelopment/code/scheduled-work-queue"><img src="https://agentmods.dev/badge/skills/helixdevelopment/code/scheduled-work-queue/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/skills/helixdevelopment/code/scheduled-work-queue"><img src="https://agentmods.dev/badge/skills/helixdevelopment/code/scheduled-work-queue.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 | $0.00075 | $0.01118 |
| Opus 5.5 | $0.00030 | $0.00447 |
| Sonnet 5.5 | $0.00015 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
scheduled-work-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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scheduled-Work Queue Skill
Purpose
Teaches an agent to use the scheduled-work MCP server to record background /
deferred work and — crucially — to verify uncertain, blocked, or overdue work
before reporting it done. This is the teeth behind the REMINDER / BACKGROUND
action-prefix (§11.4.140): when a REMINDER fires, the agent queries the queue for
work whose real outcome is not yet confirmed and re-checks it, instead of guessing
that it finished (§11.4.6 no-guessing, §11.4.108 verify-before-report).
When to use
- The operator dispatches background/deferred work ("do X later", "remind me to Y").
- A REMINDER arrives and the agent must decide what still needs confirming.
- Before an autonomous loop declares its queue empty (§11.4.87 / §11.4.126) — first
confirm no item is still
blocked/uncertain/overdue.
MCP tools (server name: scheduled-work)
create_work_item {title, description?, status?, due_at?, tags?, source?, notes?}— record a work item.status∈scheduled|in-progress|blocked|uncertain|done|cancelled(defaultscheduled);due_atis RFC3339.list_work_items {status?}— list items (optional effective-status filter, incl. derivedoverdue).get_work_item {id}— one item by id.update_work_item_status {id, status, notes?}— move an item along.mark_work_item_done {id, notes?}— close it. Only call AFTER you have verified the real outcome — put the captured evidence innotes.list_overdue_work {}— open items past their due time.list_needs_verification {}— open items (blocked/uncertain/overdue) a REMINDER MUST confirm before reporting done.
Recommended flow
- Record: on dispatching background work,
create_work_itemwith a clear title +status:"in-progress"(orblocked/uncertainif the outcome is not yet known). - On REMINDER: call
list_needs_verification. For each returned item, re-check the real system state (run the probe / read the sink / re-run the test), gather captured evidence. - Confirm-before-done: only when the evidence shows the work genuinely
succeeded,
mark_work_item_donewith the evidence path innotes. If it did NOT succeed,update_work_item_statusback toin-progress/blockedand keep working (§11.4.94 zero-idle). - Never mark done on assumption — an item left
uncertainis the honest state (§11.4.6).
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.
- 2d ago Changed · +30 lines · +56 tokens per session 35617faf6d5c
- 1mo ago First seen · 45 lines · 19 tokens per session scan A 8db5edc2865d
scheduled-work-queue is a skill published in the GitHub repository HelixDevelopment/code (2 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 1,118 once invoked, about $0.0003 per session on Opus 5.5. 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
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent. Use when a pipeline conductor session is seeded, inspected or debugged. You MANAGE one issue/PR pipeline on one repo: two columns per item (session working? item solved?), send intent, never re-derive a red yourself.
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.
feature-request
Conversational workflow for gathering user feedback and filing GitHub Issues on the Kiro Crew repository. Load when the user clicks "Request a Feature", wants to report a bug, or suggest an improvement.
goal-loop
Bootstrap a goal-driven self-improving AutoNudge loop from a goal plus an anchor directory, then run the board autonomously until the Definition of Done is met.
team-lead
Run a goal as a team when you can also do the work yourself: decide what you keep, dispatch the rest, and keep the status board honest. The delta over goal-conductor, which carries the dispatch, patrol and acceptance procedure this one points at. Load it when you are handed a goal, not a task.
goal-ledger-conductor
Deprecated alias of goal-conductor, removed next release. The work-ledger conducting procedure now lives in goal-conductor; read that skill instead.