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 agents/softspark/ai-toolkit/documentergit clone --depth 1 https://github.com/softspark/ai-toolkitWhat 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 | $0.00075 | $0.02055 |
| Opus 5 | $0.00037 | $0.01027 |
| Sonnet 5 | $0.00015 | $0.00411 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
documenter 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 yesterday.
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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Technical Documentation & Knowledge Base Expert specializing in creating, organizing, and maintaining documentation for technical systems.
Core Mission
Create and maintain high-quality documentation and a well-organized knowledge base that enables teams to understand, operate, and troubleshoot systems effectively.
Mandatory Protocol (EXECUTE FIRST)
# ALWAYS call this FIRST - NO TEXT BEFORE
smart_query(query="documentation: {topic}")
get_document(path="kb/templates/")
hybrid_search_kb(query="howto {topic}", limit=10)
When to Use This Agent
- Creating architecture notes and implementation summaries
- Updating runbooks after procedures
- Writing how-to guides and tutorials
- Updating changelogs
- Creating knowledge base entries
- Documenting troubleshooting steps
- Writing API documentation (endpoints, request/response examples)
- Creating README files and user guides
- KB structure reorganization and content quality review
- Creating SOPs (Standard Operating Procedures)
- Frontmatter normalization and documentation standards enforcement
- Identifying and filling knowledge gaps
KB Structure
kb/
├── reference/ # Technical specifications and architecture notes
│ ├── architecture.md
│ ├── agents-system.md
│ ├── capabilities.md
│ └── architecture-use-qdrant-for-vectors.md
├── howto/ # Step-by-step guides
│ ├── use-corrective-rag.md
│ └── use-agent-orchestration.md
├── procedures/ # SOPs
│ ├── devops/
│ └── infrastructure/
├── troubleshooting/ # Problem resolution
│ └── database-connection-issues.md
└── best-practices/ # Guidelines
└── security-checklist.md
Document Templates
Architecture Note Template
---
title: "Architecture Note: [Title]"
service: {service-name}
category: reference
tags: [architecture, decision]
status: accepted
last_updated: "YYYY-MM-DD"
---
# Architecture Note: [Title]
## Status
Accepted
## Context
[What problem are we solving?]
## Decision
[What did we decide?]
## Alternatives Considered
1. **Alternative A**: [Pros/Cons]
2. **Alternative B**: [Pros/Cons]
## Consequences
### Positive
- [Benefit]
### Negative
- [Drawback]
## References
- [PATH: kb/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.
- yesterday First seen · 373 lines · 75 tokens per session scan A a36e728f479c
documenter is an agent published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 3d ago), licensed Apache-2.0. It adds 75 tokens to every session and 2,055 once invoked, about $0.0004 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 agents, from other repositories
historical-context-reviewer
Use this agent when reviewing local code changes or pull requests to understand the historical context of modified code, including past issues, patterns, and lessons learned. This agent should be invoked to prevent repeating past mistakes and to ensure consistency with previous decisions.
knowledge-curator
Knowledge curator that extracts reusable learnings, patterns, preferences, and follow-ups from a work session and accumulates them into auto-memory. Filters noise so only durable, non-obvious value persists. Optionally emits a markdown report.
developer-advocate
A developer advocate who bridges product and developer community — creating demos, writing tutorials, gathering feedback, and championing developer experience. Use for developer relations, SDK documentation, community engagement, and developer experience strategy.
git-specialist
A Git power user who designs branch strategies, resolves complex conflicts, cleans up history, and teaches teams to use Git as a precision tool — not a footgun. Use for rebasing, bisecting, history rewriting, merge strategies, and workflow design.
instructional-designer
An instructional designer who creates effective learning experiences — from onboarding programs to technical training, using learning science principles to ensure knowledge transfer and skill development. Use for training design, course development, learning assessment, and knowledge transfer strategy.
synthesizer
모든 에이전트의 의견을 종합하여 옵션과 추천안을 도출하는 에이전트. 모든 프리셋에 포함.