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 shibing624/agentica --skill multi-agentgit clone --depth 1 https://github.com/shibing624/agenticaWrote 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/shibing624/agentica/multi-agent)<a href="https://agentmods.dev/skills/shibing624/agentica/multi-agent"><img src="https://agentmods.dev/badge/skills/shibing624/agentica/multi-agent/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/shibing624/agentica/multi-agent"><img src="https://agentmods.dev/badge/skills/shibing624/agentica/multi-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.01100 |
| Opus 5.5 | $0.00028 | $0.00440 |
| Sonnet 5.5 | $0.00014 | $0.00220 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
multi-agent 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with other agents
Your own work stays with you
The task you were given is yours to finish. Splitting it up is fine; the workers you split it across are your own, and their results come straight back to you:
task |
delegate |
execute(background=True) |
|
|---|---|---|---|
| Runs | in your process, read-only | its own headless session, can write | a shell command |
| You get back | the subagent's answer | the worker's final answer | exit code and log tail |
| Parallel | yes — several task calls in one message |
yes, a few at once | yes |
| Cost | cheap aux model | a whole session each | none |
Parallelism is a property of all three; it is not a reason to reach for
delegate or for another session.
The user's other live sessions (list_agents) are not a worker pool. Each one
is on its own work, often for the same person in another terminal. Handing
your task to one of them and then messaging it for progress costs two context
windows and a round trip per update to get what a task or delegate call
returns directly.
Other sessions
send_message is for coordinating with work that is not yours: another repo,
another checkout, a session the user is running for something else. You tell
it about a change of yours that affects it, ask for something only it can do or
knows, or answer what it asked you. Those sessions are running in other
terminals, and the user reads what arrives there, so send what that session
needs and nothing more.
- Address by name, never by session id. A session publishes itself before it has a session id, so for its first moments that field is empty.
- Say everything in one message. The receiver cannot see your conversation: the goal, what is out of scope, and where things are.
- A message carries the point, not the evidence. A diff, a log or a long write-up goes in a file and the message carries its absolute path.
- Delivery.
steer(default) lands between the receiver's tool calls;queuewaits for its current turn to finish. An idle session acts on either by itself. - No read receipt, no polling. A reply arrives as a new turn. End your turn instead of sleeping or checking on it.
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.
- 4d ago Changed · -48 lines · -3 tokens per session 82d1c5b142b7
- 1mo ago Changed · +4 lines 8a3f9c52051b
- 1mo ago Changed · +14 lines 159a0cd0f648
- 1mo ago First seen · 124 lines · 72 tokens per session scan A cb898ca5985b
multi-agent is a skill published in the GitHub repository shibing624/agentica (357 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 1,100 once invoked, about $0.0003 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
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors, served via preview URL.
dcf-model
Build a DCF valuation in Excel: FCF projections, WACC, terminal value, scenarios, sensitivity grids, reverse DCF. Triggers on build a DCF, what is it worth, intrinsic value, fair value, price target from cash flows.
comps-analysis
Comparable company analysis: peer set, operating metrics, valuation multiples, statistics and an implied value. Triggers on comps, trading comparables, how does it trade against peers, peer benchmarking, what multiple should it get.
company-profile
One-page company profile slide, four quadrants of overview, financial summary, share price chart and key facts. Also the compact profile paragraph when it has to sit inside a memo, a deck or a chat reply. Triggers on one-page profile, tear sheet, company snapshot, profile slide, quick profile of [company].
html-report
Self-contained styled HTML reports written to the task directory: PDF-exportable research documents with inline data, charts, and theme-aware CSS.
check-model
Audit a model somebody already built, and report on it without editing it: structure, formulas, integrity identities, source tie-out and reasonableness, ending in a routed issue log. Triggers on check my formulas, QA this spreadsheet, audit model, model review, something is off in my model, why does my balance sheet…