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/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/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/mishahanin/heading-os/queue)<a href="https://agentmods.dev/skills/mishahanin/heading-os/queue"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/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/mishahanin/heading-os/queue"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/queue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00184 | $0.01644 |
| Opus 5 | $0.00092 | $0.00822 |
| Sonnet 5 | $0.00037 | $0.00329 |
| Haiku 4.5 | $0.00018 | $0.00164 |
Grade A, and why
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 8d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/queue
The terminal-native Action Queue. Proactive agents deposit drafts here; this skill is where the CEO reviews them and SENDS - synchronously, watching each send land. It drives scripts/action-queue.py entirely in-process: no bridge daemon, no browser. The send-gate is untouched - approve is the explicit human click, and nothing is ever auto-sent.
Phase 0 - Route the request
- bare "queue" / "show my drafts" / "what's waiting" -> list (Phase 1).
- "show " -> print the full draft (Phase 2).
- "approve " / "send the first one" -> synchronous send (Phase 3).
- "edit " -> rewrite the draft (Phase 4).
- "dismiss " / "retry " -> Phase 5.
Phase 1 - List
python scripts/action-queue.py list
Read-only. Shows the active cards banded into the approve/send lane (gated sends awaiting a click) and read-only FYI context. Present them plainly with their short ids, priority, source, and draft_status. If the queue is clear, say so.
Phase 2 - Show
python scripts/action-queue.py show <id-or-prefix>
Print the full card so the CEO can read the recipient, subject, and body before deciding. Never paraphrase the draft as if it were sent.
Phase 3 - Approve = synchronous send (the watched moment)
python scripts/action-queue.py approve <id-or-prefix>
This SENDS the card right now and prints sent or send failed (reason) in the same command. For an email_send card it requires draft_status: ready_for_review (edit it first otherwise) and refuses anything that does not resolve gated. It also refuses a recipient that is still a placeholder. Fix that one with edit <id> --to, then approve again. Report the outcome exactly as the command returned it - if it failed, surface the reason and note the card is kept as send_failed for retry. Another terminal may already hold the sending claim on that card. Then approve returns blocked. That is the duplicate guard doing its job: surface the message, and do NOT retry. If a terminal died mid-send, its claim frees after five minutes; dismiss the card to clear it sooner. Approve ONE card per explicit instruction; "approve the first one" means only the first.
What ships with it
1 file 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.
- 8d ago First seen · 114 lines · 184 tokens per session scan A c6a88d724b3a
queue is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 184 tokens to every session and 1,644 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
sdlc-review
Review Kanban handoffs and route verified outcomes.
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.
design-inventory
Use to run the Claude Design to ClosedLoop pipeline against the current web-ui. Stage A inventories a design export zip into schema-validated findings (typed design units - screens, regions like nav bars, standalone components like a chat dialog; UX and behavioral changes; Storybook component reuse mapping; token…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
jira
Interact with Atlassian Jira from the terminal: search issues with JQL, view details, create issues, add comments, count matches with fast approximate-count, list projects, discover valid transitions, and change status. Includes a full JQL language reference (functions, operators, history predicates, date expressions…