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/queue-draftWrote 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-draft)<a href="https://agentmods.dev/skills/mishahanin/heading-os/queue-draft"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/queue-draft/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-draft"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/queue-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00109 | $0.01359 |
| Opus 5 | $0.00055 | $0.00679 |
| Sonnet 5 | $0.00022 | $0.00272 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
queue-draft 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queue Draft
Stage a short message as a gated draft in the Action Queue. This skill is the
reference draft-tier skill. It demonstrates, end to end, that a headless run can
DRAFT and DEPOSIT but can never APPROVE or SEND. The deposited card floors to
tier gated (an email_send draft), so it sits pending until a human runs the
approve gate. Nothing here sends.
Voice rules
- Use hyphens (
-), never double dashes. ODUN.ONE and DPI+ styled correctly. - The card is a draft, not a sent message. Never imply it was sent.
Phase 0 - Parse the input
The argument is recipient :: subject :: body (double-colon separated). Any
missing field falls back to a clearly-labelled placeholder so the card is always
well-formed:
- recipient ->
[email protected](a placeholder; the human corrects it withaction-queue.py edit <id> --to <address>before approving) - subject ->
Draft from /queue-draft - body -> the whole argument if no
::separators were given, else empty
Never invent a real recipient. A placeholder is correct; a fabricated real address is not.
Phase 1 - Compose the card
Build a single-element JSON array with one email_send draft card:
[
{
"action_type": "email_send",
"status": "pending",
"priority": "P3",
"title": "Draft: <subject>",
"to": "<recipient>",
"subject": "<subject>",
"draft_body": "<body>",
"reasoning": "Drafted by /queue-draft; GATED, awaiting explicit human approval before any send."
}
]
action_type: email_send is send-capable, so append_cards stamps tier: gated
automatically - you do not set the tier, and you must not try to lower it.
Phase 2 - Deposit (never send)
Resolve the Action Queue directory from the data root. Never hardcode a data path, because the data-path-redirect hook does not rewrite Bash. Write the one-card JSON array there with the Write tool, then deposit that file:
AQ_DIR=$(python3 -c "from scripts.utils.workspace import get_outputs_dir; print(get_outputs_dir() / 'operations' / 'action-queue')")
# Write the JSON array to "$AQ_DIR/_queue-draft-card.json" (Write tool, using the resolved absolute path)
python3 scripts/action-queue.py deposit --file "$AQ_DIR/_queue-draft-card.json"
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 · 121 lines · 109 tokens per session scan A 7b631921634b
queue-draft is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,359 once invoked, about $0.0005 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
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
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.