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 RashadAnsari/myagents --skill research-firstgit clone --depth 1 https://github.com/RashadAnsari/myagentsWrote 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/rashadansari/myagents/research-first)<a href="https://agentmods.dev/skills/rashadansari/myagents/research-first"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/research-first/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/rashadansari/myagents/research-first"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/research-first.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.00907 |
| Opus 5 | $0.00028 | $0.00453 |
| Sonnet 5 | $0.00011 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
research-first 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 9d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research First: No Guessing
Do not rely on training knowledge alone for anything that matters. Research first, then answer or implement.
When This Applies
- Unfamiliar API, SDK, or library behavior
- Security concepts, vulnerability types, cryptographic primitives
- Platform-specific behavior (OS, browser, runtime)
- Protocol specifications (HTTP, OAuth, JWT, WebSocket, etc.)
- Any version number written into a manifest, install command, Dockerfile, or CI config
- Any topic where being wrong causes a bug, vulnerability, or data loss
- Any topic where the correct answer may have changed since training cutoff
Research Order
- Read the code: grep, glob, and read relevant files in the current codebase before assuming anything about how it works
- Read official docs: fetch the official documentation or spec for the concept, not a tutorial or blog post
- Read the source: if behavior is ambiguous, read the library or runtime source
- Search broadly: if one source is insufficient, search multiple angles: official docs, spec, changelog, known issues, CVEs
- Only then answer or implement
Hard Rules
- Never guess an API signature, parameter name, or behavior: read the docs or source
- Never guess how a security mechanism works: look it up
- Never assume a behavior is the same across versions: check the version in use
- Never implement based on vague recollection: verify before writing code
- If research is inconclusive, say so explicitly: do not fill the gap with a guess presented as fact
- If something cannot be verified with available tools, say it cannot be verified: do not fabricate confidence
Dependency Versions: No Stale Dependencies
Versions from training knowledge are stale by definition. Always use the latest stable version unless the user explicitly requests otherwise.
- Never hardcode or suggest an old version number from training knowledge
- Before writing any version into a manifest or command, look up the current latest stable release
- Never use
latesttag as a substitute: resolve the actual version number and pin it explicitly - If the project already pins a version, check whether it is still current before accepting it as correct
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.
- 9d ago First seen · 69 lines · 56 tokens per session scan A 1bbb69538279
research-first is a skill published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 907 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 2026-08-31.
Other skills, from other repositories
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.