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/radarWrote 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/radar)<a href="https://agentmods.dev/skills/mishahanin/heading-os/radar"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/radar/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/radar"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/radar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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.
- medium Excessive Agency · line 27 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00191 | $0.01466 |
| Opus 5 | $0.00096 | $0.00733 |
| Sonnet 5 | $0.00038 | $0.00293 |
| Haiku 4.5 | $0.00019 | $0.00147 |
Grade A, and why
radar 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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ops-Radar
Surface what is objectively overdue and what silently degraded. This skill is the chat surface over scripts/ops-radar.py. It is a DETECTOR, not an executor: it never sends, commits, publishes, or runs a manual action for you. Outbound sends stay human-gated.
Phase 0 - Route the request
- Bare "radar" / "what's overdue" / "what am I forgetting" -> run the detector (Phase 1).
- "ack " / "silence backup" -> ack (Phase 2).
- "crunch on" / "crunch off" -> crunch (Phase 3).
Phase 1 - Run the detector
python scripts/ops-radar.py
Read-only. It computes every signal, applies ack + crunch suppression, and prints the detailed due-items view (or "all clear"). It does NOT auto-heal in this mode (heal runs on the timer). Present the result plainly, grouped by severity, and for each due Tier-B item name the one command that clears it:
backup->/backuppublish->/push-updatesweekly_review->/weekly-reviewcold_sweep->/cold-sweepodin_cadence->/odin collector/odin reflectollama_accel-> the accelerated ollama host does not answer. This machine cannot restart it, because it runs outside this OS. Work continues on the local daemon, more slowly. Tell the operator to restart it on its own host.- a critical
*_autohealline -> machine auto-heal has FAILED repeatedly; surface it, do not try to fix it inline.
State the posture: "N item(s) due" or "all clear". Never invent an item the script did not report.
Phase 2 - Ack (silence a known item)
python scripts/ops-radar.py ack <key> [--ttl 24h|7d]
Silences that one signal until the TTL expires OR its severity band worsens (worsening always re-surfaces it). Confirm what was acked and for how long. Valid keys: backup, publish, weekly_review, cold_sweep, odin_cadence, ollama, ollama_accel, memory_index, router_accuracy, queue.
Phase 3 - Crunch-mode
python scripts/ops-radar.py crunch on # suppress all Tier-B except the critical floor
python scripts/ops-radar.py crunch off # normal posture
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.
- 5d ago First seen · 111 lines · 191 tokens per session scan A 2607331dc6ab
radar is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 191 tokens to every session and 1,466 once invoked, about $0.0010 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-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.
devops-expert
Expert-level DevOps practices, culture, automation, and continuous delivery. Use when the user mentions CI/CD, automation, infrastructure, or culture, or when the task involves DevOps Culture or Culture & Process.
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
box
Box manages cloud files, sharing, search, and metadata.