Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hainamchung/agent-assistantnpx agentmods add agents/hainamchung/agent-assistant/docs-managerWrote 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/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/agents/hainamchung/agent-assistant/docs-manager"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/docs-manager.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 | $0.00015 | $0.01210 |
| Opus 5.5 | $0.00006 | $0.00484 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 4mo ago), licensed MIT. It adds 15 tokens to every session and 1,210 once invoked, about $0.0001 per session on Opus 5.5. 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
customer-support
Resolves customer issues using the organisation's documented policy and product knowledge — triage, troubleshooting, escalation, and replies that hold up.
debugger
An agent for finding the causes of program errors, failed tests, and unexpected behaviour. It handles debugging, error diagnosis, bug fixing, and system troubleshooting.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.