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 ApexIQ/skillsmith --skill how_to_researchgit clone --depth 1 https://github.com/ApexIQ/skillsmithWrote 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/apexiq/skillsmith/how_to_research)<a href="https://agentmods.dev/skills/apexiq/skillsmith/how_to_research"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/how_to_research/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/apexiq/skillsmith/how_to_research"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/how_to_research.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 | $0.00024 | $0.00415 |
| Opus 5 | $0.00012 | $0.00208 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
how-to-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 10d 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
🔍 How to Research
Rule: Don't guess. Verify.
1. Internal Research (Codebase)
- Map the Territory:
- List directory structure to understand organization.
- Read
README.md,package.json, orrequirements.txtfirst.
- Search Smart:
- Use grep/ripgrep to find usage of functions/classes.
- Search for configuration files.
- Trace the Flow:
- Start at the entry point (
main.py,index.tsx,app.ts). - Follow imports to understand dependencies.
- Start at the entry point (
2. External Research (Web)
- Query Engineering:
- ✅ "FastAPI rate limiting middleware best practices 2024"
- ❌ "FastAPI slow"
- Trusted Sources:
- Official documentation (React, FastAPI, etc.).
- GitHub Issues (for bug workarounds).
- Engineering Blogs (Uber, Netflix, Stripe for architecture).
- Stack Overflow (verify answers are up-to-date).
3. Synthesis
- Adapt, don't copy-paste. Findings must fit your project context.
- Cite Sources: Note where you found solutions in code comments.
- Cross-reference: Verify information from multiple sources.
Examples
- Understanding a new library: Official docs -> GitHub examples -> Blog tutorials.
- Debugging an error: Error message in quotes -> Search GitHub Issues -> Stack Overflow.
Guidelines
- Spend 5-10 mins researching before asking for help.
- Document findings for future reference.
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.
- 10d ago First seen · 50 lines · 24 tokens per session scan A 71c49efd6abc
how-to-research is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 415 once invoked, about $0.0001 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
pptx
Extract text from Microsoft PowerPoint presentations.
xlsx
Extract data from Excel and CSV files.
agent-teams
Multi-agent team orchestration with native Agent Teams. Trigger when the user wants to launch a team of agents, coordinate parallel work with inter-agent communication, or use swarm mode.
ops-infra-code
Infrastructure as Code with Terraform/OpenTofu. Trigger to create modules, configure backends, write idiomatic HCL, or audit infrastructure.
Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…
easd-verify
Run the final EASD integration and evidence gate against accepted AC policies, then prepare a convergence recommendation. Use after implementation and any required independent review; not for task-local code review or ordinary tests outside EASD.