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 skills add xg-gh-25/SwarmAI --skill s_radar-todogit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_radar-todo)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_radar-todo"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_radar-todo/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/xg-gh-25/swarmai/s_radar-todo"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_radar-todo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Prompt Injection · line 189 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00106 | $0.04135 |
| Opus 5 | $0.00053 | $0.02067 |
| Sonnet 5 | $0.00021 | $0.00827 |
| Haiku 4.5 | $0.00011 | $0.00413 |
Grade A, and why
radar-todo 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 12d 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ToDo Skill
Skill NAME (
s_radar-todo) is a legacy identifier — kept stable. The SURFACE is the left-nav ToDo card (nav-todo→swarm:show-todo→ToDoOverlay, a fullscreen Flow|History workbench). There is NO "Radar sidebar" anymore.
Manage ToDo items surfaced in the left-nav ToDo card/overlay. ToDos are stored in
SQLite (~/.swarm-ai/data.db) and displayed in the ToDo overlay's Flow board.
Core principle: Every todo is a self-contained work packet. When a user drags a todo into a chat tab or says "work on this todo", the agent must be able to start executing immediately — no re-discovery, no context hunting.
Tool
python3 {SKILL_DIR}/scripts/todo_db.py <command> [options]
Work Packet Schema (linked_context)
Every todo's linked_context field stores a JSON object with structured context:
{
"files": ["backend/core/session_unit.py", "desktop/src/hooks/useChatStreamingLifecycle.ts"],
"design_docs": ["Knowledge/Designs/2026-03-21-append-message-design.md"],
"commits": ["81f596c", "a070ca3"],
"sessions": ["3af6258b"],
"memory_refs": ["COE:2026-03-20:big-bang-refactor", "Lesson:2026-03-22:invariants"],
"next_step": "Extract _handle_agent_task_result into dispatch table in session_unit.py",
"acceptance": "Append message queues during stream, last-message-wins, no content loss on tab switch",
"blockers": ["Need to verify queue drain in finally block handles CancelledError"],
"notes": "Design doc v2 approved. Queue-based approach — never stops stream."
}
| Field | Required? | Purpose |
|---|---|---|
next_step |
YES | Concrete first action. Not vague — an actual step the agent executes. |
files |
YES for code todos | Source files to read/modify. Relative to swarmai repo root. |
acceptance |
Recommended | How to know it's done. "Tests pass" is not enough — describe the behavior. |
design_docs |
If exists | Design docs or specs. Agent reads these before starting. |
commits |
If relevant | Related git commits for context (e.g. prior fix attempts). |
sessions |
If relevant | Chat session IDs where this was discussed. |
memory_refs |
If relevant | MEMORY.md entries (COEs, lessons, decisions) that apply. |
blockers |
If any | What's preventing progress. High priority if blockers exist. |
notes |
Optional | Free-form context that doesn't fit elsewhere. |
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.
- 12d ago First seen · 367 lines · 106 tokens per session scan A 2de760b4215e
radar-todo is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 4,135 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 2026-08-30.
Other skills, from other repositories
digest
NOTE: this skill requires connected chat / email / project-tracker / docs MCPs, which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Cross-tool rollup of what's pending, what shipped, and what's blocked across chat / email / project tracker /…
roadmap
Render a per-project feature roadmap — a Band×Status grid (Shipped/Current/Next/Later × done/in-progress/blocked/buildable) synthesized from CLAUDE.md + PROGRESS.md, persisted to a committed ROADMAP.md with staleness-aware refresh. Modes: '/roadmap' (nearest project), '/roadmap ' (a projectslist tag), '/roadmap…
stitch
Build or verify cross-repo STITCH.md linking backend + frontends in a product group. Modes: create, verify, diff, section. Uses CODEMAPs as drift source by default. Trigger: '/stitch create ', '/stitch diff '.
aria-assist
Morning product-management review across all your projects. Use when the user runs /aria-assist, asks for a morning review / daily PM digest / "what should I do today across my products", or when the launchd job fires it headless. Two modes - generate (headless: read facts, deep-review ACTIVE projects, apply logged…
backlog
View and manage pending backlog items. Use when user says '/backlog', '/backlog insights', '/backlog clear', 'what's pending', 'show backlogs', 'check backlog status'. (Code port — ADR-094.).
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…