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 zenx0x/allinluna --skill research-routes-exploregit clone --depth 1 https://github.com/zenx0x/allinlunaWrote 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/zenx0x/allinluna/research-routes-explore)<a href="https://agentmods.dev/skills/zenx0x/allinluna/research-routes-explore"><img src="https://agentmods.dev/badge/skills/zenx0x/allinluna/research-routes-explore/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/zenx0x/allinluna/research-routes-explore"><img src="https://agentmods.dev/badge/skills/zenx0x/allinluna/research-routes-explore.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 | $0.00071 | $0.00326 |
| Opus 5.5 | $0.00028 | $0.00130 |
| Sonnet 5.5 | $0.00014 | $0.00065 |
| Haiku 4.5 | $0.00007 | $0.00033 |
Grade A, and why
research-routes-explore 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 2mo 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.
What it actually says
Research Routes Explore
Explore without collapsing uncertainty. The Research Pack is append-only and route-neutral.
- Start from the supplied question, problem, frame, repository, artifact, or arbitrary context; record it as the starting point.
- Build a terrain map and shared backbone before selecting a route.
- Keep at least two viable routes or explicitly record why only one route is available. Branch routes rather than overwriting them.
- Design probes and experiments with boundary conditions and failure regimes. Record observations as evidence with polarity and provenance.
- Preserve contradictions and unknowns. A null or failure result is still an observation and does not silently invalidate a route.
- Keep candidate inference, experiment authorization, HumanDecision, implementation, and canonical promotion as separate transitions.
- Compare mature methods and alternative explanations when the question is scientific; preserve their scope and limitations.
- Record failures with polarity and what did not fail, then use rewind, lessons, and reopened problems to recover without rewriting history.
- Do not treat a terrain map as a route choice, experiment authorization, implementation, HumanDecision, or canonical-state promotion.
The shared semantic model and schema are authoritative for node, relation, polarity, route, and lifecycle values.
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.
- 2mo ago First seen · 21 lines · 71 tokens per session scan A ec0454c9b80b
research-routes-explore is a skill published in the GitHub repository zenx0x/allinluna (63 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 326 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
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.