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 existential-birds/beagle --skill subagent-promptgit clone --depth 1 https://github.com/existential-birds/beagleWrote 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/existential-birds/beagle/subagent-prompt)<a href="https://agentmods.dev/skills/existential-birds/beagle/subagent-prompt"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/subagent-prompt/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/existential-birds/beagle/subagent-prompt"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/subagent-prompt.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 Agent Snooping · line 63 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 63 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00116 | $0.01429 |
| Opus 5.5 | $0.00046 | $0.00572 |
| Sonnet 5.5 | $0.00023 | $0.00286 |
| Haiku 4.5 | $0.00012 | $0.00143 |
Grade A, and why
subagent-prompt 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-Agent Orchestration Prompt
Produce a single, self-contained prompt that the user can paste into a new agent session (one that supports sub-agents) to execute the work discussed in this conversation. The new session is the orchestrator: it dispatches a sub-agent per task and only synthesizes results — it does not implement code itself.
Goal
Hand off the current session's work to a fresh context window in a form that:
- Runs to completion without needing the user to babysit each step
- Uses one sub-agent per task so each task has its own context window
- Forces each sub-agent to verify its own work before reporting back
- Leaves the orchestrator with enough material to confirm the whole job is functional at the end
Gates
Complete in order. Do not advance until the Pass when condition holds.
- Source material identified — Pass when: You can point to the concrete artifacts this prompt will hand off (a plan file, a checklist, a list of changes the user described, etc.). If the conversation has only vague intent, ask the user what the prompt should cover before drafting.
- Task decomposition explicit — Pass when: You have a numbered list of tasks (or you can point to one already on disk) where each task is small enough for one sub-agent to own end-to-end. If the work is monolithic, decompose it before drafting the prompt.
- Verification per task specified — Pass when: For every task, you have named the concrete check a sub-agent must run before reporting success (typecheck command, test command, lint, file inspection, etc.). "Verify it works" is not a pass.
- Prompt drafted and self-contained — Pass when: The drafted prompt would make sense to a fresh agent session with zero memory of this conversation: it names paths, names tools, names verification commands, and names the success condition.
What the Generated Prompt Must Contain
Draft the handoff prompt as a single fenced block the user can copy. It must include, in this order:
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 · 64 lines · 116 tokens per session scan A 56bdf49dab6f
subagent-prompt is a skill published in the GitHub repository existential-birds/beagle (84 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 116 tokens to every session and 1,429 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
coding-standards
Use when establishing or reviewing Go/Python coding conventions for naming, structure, readability, maintainability, imports, typing, errors, and tests.
codex-rule-router
Use when applying GG coding, review, testing, security, performance, workflow, Go, or Python rule packs in Codex, especially for Go/Python backend repositories.
pr-to-go-linter
Generate a new pkg/linters analyzer from a merged or open PR pattern.
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…
code-review
You are a senior code reviewer. You receive diffs via stdin.
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence, or to make a feature reel (see reel mode…