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 OutlineDriven/odin-gemini-cli-extension --skill researchgit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/research)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/research"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/research.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 5.1 | $0.00087 | $0.00888 |
| Opus 5 | $0.00044 | $0.00444 |
| Sonnet 5 | $0.00017 | $0.00178 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
research 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 7d 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.
This is a copy
100% identical to research — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Command
Read-only external knowledge gathering. Walk the 5-tier source ladder; cite every claim to a primary source; flag training-data-only assertions explicitly. Do NOT write, edit, or commit files.
When to Apply / NOT
Apply:
- Library/framework/SDK/API docs — signatures, config options, migration
- Version-specific behavior — changelogs, deprecations, breaking changes
- Vendor announcements, RFCs, public web technical content
- Any named library, framework, SDK, API, CLI tool, or cloud service
NOT apply:
- Questions about a local repo's code — use a codebase exploration workflow instead
- Autonomous goal-directed research loops (multi-step, agent-driven)
- Implementation or file editing
Process
- Identify subject — extract the library, framework, SDK, API, CLI, or topic from the user's message. Capture version if stated (e.g.,
[email protected]). If version unstated, resolve latest stable at Tier 1. - Resolve identifier — look up the canonical name and version from the library's official documentation surface. If no dedicated doc tool is available, use the subject name as the search query and proceed.
- Walk the source ladder — start at Tier 1; proceed to the next tier only on hard failure (source unavailable, no results, clearly non-authoritative hit). State which tier was skipped and why.
- Cross-reference — every factual claim must cite at least one primary source URL. Assertions derived solely from training data must carry
[Speculative — training data only]. - Synthesize — produce Required Output with source URLs and
library@versionidentifiers.
Source Ladder
Priority order (canonical): 1) Official docs 2) API refs 3) Books/papers 4) Tutorials 5) Community
If a source category is unavailable or returns no authoritative results, skip it and move to the next tier — do not halt.
| Tier | Priority | Source type | Use when |
|---|---|---|---|
| 1 | Official docs | Library/framework official documentation site; SDK reference pages | Named library/framework/SDK with a published doc surface |
| 2 | API refs | API reference pages; repository README and docs folders | API signatures, types, configuration keys, repo-architecture details |
| 3 | Books/papers | RFCs; academic papers; vendor whitepapers; standards documents | Standards-body publications, deep technical specifications |
| 4 | Tutorials | Tutorial articles; blog posts; vendor how-to guides | Example-driven walkthroughs when reference docs are insufficient |
| 5 | Community | Repository issues and discussions; community forums; Q&A threads | Real-world usage patterns, upstream known issues, community workarounds |
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.
- 7d ago First seen · 58 lines · 87 tokens per session scan A a71e2ba01676
research is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 888 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to research, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.