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 agentmods add skills/haowenhou/agenticresearchwiki/import-notesnpx skills add HaowenHou/AgenticResearchWiki --skill import-notesgit clone --depth 1 https://github.com/HaowenHou/AgenticResearchWikiWrote 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/haowenhou/agenticresearchwiki/import-notes)<a href="https://agentmods.dev/skills/haowenhou/agenticresearchwiki/import-notes"><img src="https://agentmods.dev/badge/skills/haowenhou/agenticresearchwiki/import-notes.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 | $0.00022 | $0.01301 |
| Opus 5 | $0.00011 | $0.00651 |
| Sonnet 5 | $0.00004 | $0.00260 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
import-notes 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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
import-notes
Import the user's existing research notes (scattered across other notes apps, folders, or pasted directly into the prompt) into this wiki, file them in the right places per this repo's current conventions, and update the relevant indexes.
When to trigger
The user says any of (or anything semantically similar):
- "import notes" / "integrate my existing notes" / "pull these notes in"
- "migrate from the old project / another notes app"
- Hands you a folder path, a batch of files, or a big blob of pasted content and asks you to "classify and file it per the rules"
Input forms
Two input modes are supported (mix is fine too):
- Folder: the user gives a directory path containing anything the Agent can read (
.md/.txt/.pdf/.docx/.html/ web clippings / code comments, etc.). Walk and read. - Inline prompt: the user pastes note content directly into the conversation. Split into individual items by blank lines or headings.
If the user gives neither a path nor inline content, proactively ask.
Workflow
Step 1: Learn the current rules of this repo
Do NOT hardcode classification rules. The only premise of this skill is: this repo already has a set of live conventions. The actual routing must be read by the Agent from the repo on the fly:
- Read
CLAUDE.md— learn the reading order, update rules, and do-not-read areas - Read
Overview.md— learn the project skeleton, task navigation, and doc-organization conventions - Read each module's Overview (
Data/DataOverview.md,Training/TrainingOverview.md,Eval/EvalOverview.md,ResearchNotes/ResearchNotesOverview.md, etc.) — learn what already exists and the naming conventions - If the repo has additional
XXX-conventions.md/supported-XXX.mdstyle docs, read those too
Based on the above, form "this repo's current classification rules" as the basis for this import.
Step 2: Collect the source material
- Folder input: list all files, read each one
- Inline input: split into items by heading/blank line
- Assign an internal id to each item (e.g.
src-01,src-02…) for later reference when presenting the plan
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.
- 5d ago First seen · 114 lines · 22 tokens per session scan A efc0e100dac3
import-notes is a skill published in the GitHub repository HaowenHou/AgenticResearchWiki (29 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 1,301 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 2026-08-30.
Other skills, from other repositories
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
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…
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.