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/elibarak12/elliot/compose-skillnpx skills add EliBarak12/Elliot --skill compose-skillgit clone --depth 1 https://github.com/EliBarak12/ElliotWrote 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/elibarak12/elliot/compose-skill)<a href="https://agentmods.dev/skills/elibarak12/elliot/compose-skill"><img src="https://agentmods.dev/badge/skills/elibarak12/elliot/compose-skill.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.01421 |
| Opus 5 | $0.00033 | $0.00711 |
| Sonnet 5 | $0.00013 | $0.00284 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
compose-skill 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Skill Workflow
You are turning a recurring multi-tool chain into one named session skill. A skill is a step list — each step is a tool call whose result the next step can reference — that the runtime exposes as a single MCP tool to downstream agents. Done well, it collapses three or four agent turns into one.
Vocabulary note. "Skill" here is the runtime concept (a chained tool sequence stored in the session, defined via
elliot_create_skill). It is NOT a SKILL.md file like the one you are reading — those are workflow guides for you, the agent. Don't conflate them.
When a skill is worth composing
Compose a skill when all of these are true:
- The job-to-be-done always needs ≥ 2 tool calls, in the same order.
- The first tool's output feeds the second's parameters (e.g. "look up the customer id, then summarise their orders").
- The downstream agent's prompt does not need to see the intermediate results — only the final answer.
If the agent often branches between two different second-step tools based on
the first tool's output, that's a workflow, not a deterministic chain — but
it can still be a connector skill. Author it as a prose skill: call
elliot_create_skill with instructions (markdown describing the workflow,
branches and all) and when_to_use, and leave steps empty. On export it
becomes a SKILL.md guide alongside the connector's tools — exactly like the
hand-written guides Elliot ships for itself. A skill may carry both steps
(the happy-path chain) and instructions (the surrounding judgement).
Steps
1. Confirm the chain
Call elliot_list_tools to see what's registered. Identify the exact tool
ids the chain uses and read each with elliot_get_tool(tool_id) to confirm
its parameters and what it returns.
2. Sketch the steps
For each step, decide:
alias— short name you'll reference the result by (e.g.customer,orders).tool_id— the registered tool's id.params— the literal parameter dict. To thread a field of an earlier step's first result row into this one, reference it by{{ steps.<alias>.<field> }}— e.g. a step aliasedcustomerexposes its first row'sidas{"user_id": "{{ steps.customer.id }}"}. This is the exact binding the runtime resolves;{{ customer.rows[0].id }}and other shapes are not valid and fail withSKILL_TEMPLATE_UNRESOLVED.
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 First seen · 120 lines · 66 tokens per session scan A 773df2edc17f
compose-skill is a skill published in the GitHub repository EliBarak12/Elliot (11 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,421 once invoked, about $0.0003 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
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…