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 IsaiaScope/ai --skill iso-spawngit clone --depth 1 https://github.com/IsaiaScope/aiWrote 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/isaiascope/ai/iso-spawn)<a href="https://agentmods.dev/skills/isaiascope/ai/iso-spawn"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-spawn/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/isaiascope/ai/iso-spawn"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/iso-spawn.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 | $0.00102 | $0.02964 |
| Opus 5.5 | $0.00041 | $0.01186 |
| Sonnet 5.5 | $0.00020 | $0.00593 |
| Haiku 4.5 | $0.00010 | $0.00296 |
Grade A, and why
iso-spawn 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 1mo 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iso-spawn
Launches a codex or claude agent in a fresh herdr tab, in the current workspace
(resolved from $HERDR_PANE_ID, immune to UI focus). Full permissions by default, optional
prompt injected and auto-run, delivered in the background so the caller never blocks.
You are the orchestrator. A spawned agent runs independently in its own pane — it does not call you back when it finishes. iso-spawn gives you the verbs; you own the lifecycle: launch it, watch it, talk to it, collect its work, tear it down. When this skill is used inside another skill, that parent skill owns the lifecycle and decides when each spawned agent is killed. Everything below is your control surface.
Operating a spawned agent
Every agent moves through five phases. Each phase has one verb and answers one question:
| phase | verb(s) | the question you're answering | anchor |
|---|---|---|---|
| 1. Launch | spawn / deliver |
sync or async? full-perm or --safe? |
prints a TERM |
| 2. Monitor | status, herdr agent wait |
is it working / idle / blocked? |
<TERM> |
| 3. Interact | send |
unblock it, course-correct, follow up | <TERM> |
| 4. Recover | recover |
pull its result (output | chat) |
<TERM> |
| 5. Tear down | cleanup (--kill, --orphaned) |
kill the tab, reap the sidecar, no leaks | <TERM> |
The single anchor for phases 2–5 is the TERM (herdr terminal id) printed at launch.
Capture it. Every other verb takes one <TERM>; N agents = N independent TERMs.
Pick your launch shape
There are three launch shapes. Choose by what you want back:
| you want | use | blocks? |
|---|---|---|
| one task done, result back, tab gone (the common case) | deliver … --kill |
yes |
| result back, agent kept alive for follow-ups | deliver … (no --kill) |
yes |
| run many agents in parallel, collect later | async spawn ×N, then poll |
no |
| a long job while you keep working | async spawn, poll later |
no |
What ships with it
14 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.
- README.md 5.7 KB
- REFERENCE.md 12 KB
- scripts/lib/agentkind.sh 2.1 KB runs code
- scripts/lib/cleanup.sh 1.5 KB runs code
- scripts/lib/deliver.sh 3.0 KB runs code
- scripts/lib/herdr.sh 4.3 KB runs code
- scripts/lib/transcript.sh 4.9 KB runs code
- scripts/lib/wait.sh 4.7 KB runs code
- scripts/recover.py 2.7 KB runs code
- scripts/spawn.sh 14 KB runs code
- tests/fixtures/claude.jsonl 297 B
- tests/fixtures/codex.jsonl 515 B
- tests/fixtures/empty.jsonl 174 B
- tests/run.sh 25 KB runs code
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.
- 1mo ago First seen · 231 lines · 102 tokens per session scan A e97593130768
iso-spawn is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed 7d ago), licensed MIT. It adds 102 tokens to every session and 2,964 once invoked, about $0.0004 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
remotion-best-practices
Best practices and domain knowledge for building videos programmatically with Remotion (videos in React/TypeScript, rendered to MP4). Use whenever writing or editing Remotion code — scaffolding a video project, animating with interpolate/spring over useCurrentFrame(), sequencing scenes and transitions…
remotion-create
Creating a new Remotion video.
remotion-interactivity
Best practices for writing Remotion animations that stay intuitive for agents and editable in Remotion Studio Visual Mode.
excalidraw-visual-designer
Create and revise editable visual drawings directly in the Excalidraw website through the in-app browser. Use when the user asks Codex to draw in Excalidraw or update an Excalidraw canvas, including diagrams, flowcharts, architecture sketches, process maps, infographics, teaching visuals, product explanation graphics…
wechat-sticker-maker
A tool that cuts a grid image into separate WeChat stickers and resizes the files to WeChat’s required formats. It supports common six-, nine-, and twelve-panel layouts.
software-in-worten
Übersetzt zwischen Benutzeroberfläche und Text — in beide Richtungen. Aus einer beschriebenen Oberfläche wird ein Skill; aus einem Skill wird eine Oberfläche. Nutzen, wenn eine Anwendung entworfen wird und der Ablauf noch unklar ist, wenn ein bestehendes Werkzeug als Skill verfügbar gemacht werden soll, wenn…