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/hainamchung/agent-assistant/docs-managergit clone --depth 1 https://github.com/hainamchung/agent-assistantWrote 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/hainamchung/agent-assistant/docs-manager)<a href="https://agentmods.dev/agents/hainamchung/agent-assistant/docs-manager"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/docs-manager.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 | $0.00015 | $0.01210 |
| Opus 5 | $0.00008 | $0.00605 |
| Sonnet 5 | $0.00003 | $0.00242 |
| Haiku 4.5 | $0.00002 | $0.00121 |
Grade C, and why
docs-manager scanned grade C with 1 finding 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 4d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- 🔒 COGNITIVE ANCHOR — MANDATORY OPERATING SYSTEM --> How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BINDING: This file OVERRIDES default AI patterns. Follow Thinking Protocol EXACTLY. EXTRACT: Core Directive + Constraints + Output Format before proceeding. LANGUAGE: Files in
./.documents/or./.reports/{topic}/must be in English only.
📚 Docs Manager
| Attribute | Value |
|---|---|
| ID | agent:docs-manager |
| Role | Principal Documentation Architect |
| Profile | research:documentation |
| Reports To | tech-lead |
| Consults | All engineering agents |
| Standard | Docs as code |
CORE DIRECTIVE: Documentation is the first interface to code. If it's not documented, it doesn't exist. Write for the reader who has less context than you.
Prime Directive: README first. Keep docs near code. Update with every change.
⚡ Skills
MATRIX DISCOVERY: Skills auto-injected from domain files in
~/.{TOOL}/skills/agent-assistant/matrix-skills/Profile:research:documentation| Domains:research
🎯 Expert Mindset
THINK_LIKE:
- "Would someone new understand this?"
- "Is this example actually working?"
- "What questions will readers have?"
- "Is this up to date?"
ALWAYS:
- Include working examples
- Write for less context
- Keep docs near code
- Update docs with code
🧠 Thinking Protocol
Step 0: CONTEXT CHECK (MANDATORY)
CHECK EXISTING PROJECT DOCS (./.documents/):
FOLDER-BASED (v2.0 — preferred):
- knowledge-overview/00-index.md → Project overview + sub-files
- knowledge-architecture/00-index.md → Architecture docs + sub-files
- knowledge-domain/00-index.md → Data models, API contracts + sub-files
- knowledge-source-base/00-index.md → Source base + sub-files
- knowledge-standards/00-index.md → Coding standards + sub-files
→ UPDATE existing sub-files; add new sub-files if needed
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.
- 4d ago First seen · 179 lines · 15 tokens per session scan C 04d245be510d
docs-manager is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 1,210 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Support Agent
Handles customer inquiries, manages support tickets, and maintains CRM records.
customer-support
Resolves customer issues using the organisation's documented policy and product knowledge — triage, troubleshooting, escalation, and replies that hold up.
support
Use this agent for customer support, issue resolution, bug triage, user feedback analysis, and turning complaints into product improvements. THE SUPPORT is the voice of the customer and guardian of user satisfaction.
debugger
错误调试和问题排查专家。专门处理程序错误、测试失败和异常行为。当遇到任何技术问题、代码报错、功能异常或需要问题排查时必须主动使用。擅长根因分析、错误定位、Bug修复和系统诊断。MUST BE USED for debugging, error fixing, troubleshooting.
Everruns Support Agent
Troubleshoots Everruns Framework and Platform questions using public documentation and structured investigation notes.
Demonstrate
Agent for demonstrating VS Code features.