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 allemaar/open-skills --skill caller-optionsgit clone --depth 1 https://github.com/allemaar/open-skillsWrote 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/allemaar/open-skills/caller-options)<a href="https://agentmods.dev/skills/allemaar/open-skills/caller-options"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/caller-options/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/allemaar/open-skills/caller-options"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/caller-options.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 | $0.00090 | $0.01734 |
| Opus 5 | $0.00045 | $0.00867 |
| Sonnet 5 | $0.00018 | $0.00347 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade A, and why
caller-options 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 11d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/caller-options
Caller Options (COP) makes a skill's hidden choices visible. When a participating skill runs, COP detects whether the invocation has material optionality along two dimensions, evaluates the live options, and surfaces them to the caller — instead of the skill silently picking. The caller (a human, or another agent) decides.
- Venue — who executes:
inline(the active agent),delegated(one primed sub-agent, while the active agent orchestrates — the "agentic counterpart"), orfan-out(N parallel sub-agents). - Mode — which path of the skill, when the skill already has more than one.
COP is invoked two ways: automatically, when a skill carrying the COP opt-in block is triggered; or directly, as /caller-options <task or skill> for an ad-hoc routing decision.
The protocol — five steps
COP always runs in the active agent — the venue decision cannot itself be delegated.
- Triage. Read the triggered skill's
caller-optionsdeclaration and the task. If exactly one venue and one mode clearly dominate, skip straight to execute — do not prompt the caller. This anti-nag gate resolves most invocations. - Enumerate. List the viable
mode × venuecombinations. Dropdelegated/fan-outif the skill is on the never-delegate list, is self-orchestrating (spawns its own sub-agents — wrapping it would nest to depth 2), or if a resolved-invocation marker is present (depth guard). - Assess. Evaluate the survivors for cost, context hygiene, and fit. Two or fewer options → compare inline. Three or more → invoke
/insight-assess. - Surface. Human caller →
AskUserQuestion, recommended option first. Agent caller → state the options and the pick visibly, honoring the skill'sdefault-policy. - Execute. Run the chosen combination. For
delegated/fan-out: build a primed brief (reusing thehandoffbrief schema), prepend theCOP-RESOLVEDmarker block (literal format inOPT-IN-BLOCK.md) — it carriesdepth: 1, so the sub-agent runs its skill and any COP participant it triggers inline and never re-enters COP; spawn; orchestrate; inspect the diff/output before accepting.
What ships with it
4 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.
- 11d ago First seen · 85 lines · 90 tokens per session scan A 3c32c5ece31a
caller-options is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 1,734 once invoked, about $0.0005 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
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
media
Skill "media" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
_data
Skill "_data" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.