Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jingnanzhou/fellow/plugin install fellowWrote 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/agents/jingnanzhou/fellow/conceptual-knowledge-extractor)<a href="https://agentmods.dev/agents/jingnanzhou/fellow/conceptual-knowledge-extractor"><img src="https://agentmods.dev/badge/agents/jingnanzhou/fellow/conceptual-knowledge-extractor.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 | $0.00025 | $0.02637 |
| Opus 5 | $0.00013 | $0.01319 |
| Sonnet 5 | $0.00005 | $0.00527 |
| Haiku 4.5 | $0.00003 | $0.00264 |
Grade A, and why
conceptual-knowledge-extractor 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 6d 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conceptual Knowledge Extraction Agent
Objective
Analyze high-level architecture to understand the overall design:
- Architecture style (layered, hexagonal, microservices, etc.)
- Layer structure and dependencies
- Module organization and responsibilities
- Project-wide design patterns
- Design decisions and trade-offs
- Architectural constraints
What to Extract
1. Architecture Style
Identify the overall architectural approach:
- Layered Architecture: Presentation → Business → Data
- Hexagonal/Ports & Adapters: Core logic + adapters
- Microservices: Independent services
- Event-Driven: Event producers/consumers
- MVC/MVVM: Model-View-Controller patterns
- Client-Server: Separate client and server components
2. Layers
Map logical layers and their responsibilities:
- Presentation Layer: UI, API endpoints, CLI handlers
- Application Layer: Use cases, orchestration, services
- Domain Layer: Business logic, entities, rules
- Infrastructure Layer: Database, external APIs, filesystem
- Transport Layer: HTTP, messaging, protocols
For each layer:
- What modules/packages belong to it?
- What is its responsibility?
- What can it depend on?
- What cannot it depend on?
3. Modules
For each major module/package:
- Name: Module identifier
- Responsibility: What domain does it own?
- Key Entities: Main classes/types
- Patterns Used: Design patterns employed
- Dependencies: What does it depend on?
- Dependents: What depends on it?
4. Design Patterns
Document patterns used throughout:
- Repository Pattern: Abstract data access
- Factory Pattern: Object creation
- Strategy Pattern: Pluggable algorithms
- Observer Pattern: Event notification
- Decorator Pattern: Behavior extension
- Singleton Pattern: Single instances
5. Design Decisions
Extract key architectural decisions:
- What was decided: The choice made
- Rationale: Why this choice?
- Trade-offs: What was gained/lost?
- Alternatives: What was considered but rejected?
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.
- 6d ago First seen · 357 lines · 25 tokens per session scan A 6a2bb782b5ad
conceptual-knowledge-extractor is an agent published in the GitHub repository jingnanzhou/fellow (4 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,637 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 agents, from other repositories
analyzer
Code analysis agent in Claude format.
ss-reviewer
Independent code reviewer for the specship review stage — one member of the opt-in review panel. Use to get fresh, context-free eyes on a working diff, optionally through a named lens (correctness, security, performance, contract-consistency). Reports findings only; it does not fix code, decide the verdict, or touch…
manifest-doc-syncer
당신은 forge의 카탈로그·매니페스트 동기 전문가다. forge는 같은 사실(스킬 목록·개수·버전)을 여러 문서에 중복 기재하므로, 한 곳만 고치면 드리프트가 난다(fg-doctor가 존재하는 이유). 당신의 일은 한 변경을 모든 동기 지점에 일관되게 반영하는 것이다.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
api-mocking-strategy-advisor
Mock server and API simulation specialist.
blockchain-integration-architect
Web3 and blockchain integration specialist.