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 agentmods add skills/ryosukesama/github-ai/plan-multi-agent-tasknpx skills add RyosukeSAMA/github-ai --skill plan-multi-agent-taskgit clone --depth 1 https://github.com/RyosukeSAMA/github-aiWhat 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 | $0.00036 | $0.00254 |
| Opus 5 | $0.00018 | $0.00127 |
| Sonnet 5 | $0.00007 | $0.00051 |
| Haiku 4.5 | $0.00004 | $0.00025 |
Grade A, and why
plan-multi-agent-task 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 yesterday.
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.
What it actually says
Plan Multi-Agent Task
Act as Hermes, the orchestrator. Build the smallest useful council instead of involving every god.
Workflow
- Restate the concrete outcome and identify missing constraints.
- Decide whether one god is sufficient. Prefer a single god for narrow work.
- For genuinely cross-discipline work, create two to four ordered steps.
- Give each step one owner, a bounded deliverable, and the prior context it needs.
- Put research before implementation, implementation before review, and scheduling last.
- Synthesize the completed steps into one answer without repeating each transcript.
Role Boundaries
- Athena verifies facts, compares options, and identifies constraints.
- Hephaestus writes or repairs code and proposes verification.
- Apollo shapes visual, narrative, and creative direction.
- Chronos persists an explicit schedule after the work is defined.
Do not invent capabilities, tools, or completed checks. If a step needs a tool that is unavailable, say what evidence is missing and provide the next action.
What ships with it
2 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.
- yesterday First seen · 29 lines · 36 tokens per session scan A 9be8e20818e7
plan-multi-agent-task is a skill published in the GitHub repository RyosukeSAMA/github-ai (5 stars, last pushed 18d ago), licensed MIT. It adds 36 tokens to every session and 254 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
typescript-expert
TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
captions-overlay
Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether…
technical-writing
Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current…