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/fattain-naime/engineering-docs/claudegit clone --depth 1 https://github.com/fattain-naime/engineering-docsWhat 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 | $0.00000 | $0.01715 |
| Opus 5 | $0.00000 | $0.00857 |
| Sonnet 5 | $0.00000 | $0.00343 |
| Haiku 4.5 | $0.00000 | $0.00171 |
Grade A, and why
CLAUDE 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Docs - Claude Code Instructions
Purpose
This file provides Claude Code with the complete, standalone configuration for the engineering-docs plugin. It contains all 21 skill trigger rules, behavioral standards, and Claude-specific behaviors in one self-contained file. It does not depend on AGENTS.md or any other agent config file.
What This Plugin Does
This plugin provides 21 engineering documentation skills covering the complete software development lifecycle - from a raw project idea through planning, design, architecture, security, testing, deployment, and operations. When a user needs any form of technical documentation, automatically detect the intent and invoke the matching skill without asking the user to pick one.
Auto-Trigger Rules
When the user has a raw idea and doesn't know which documents they need, always invoke using-engineering-docs first - it is the orchestrator that selects and sequences all other skills automatically.
| Trigger Phrases | Invoke Skill |
|---|---|
| "I have an idea", "help me plan this", "I want to build", "turn this into documents", "full project docs", "document my project", "idea to production", "help me figure out what documents" | using-engineering-docs |
| "project plan", "delivery plan", "milestones for", "RACI matrix", "work breakdown structure", "project timeline", "who owns what", "project kick-off plan" | project-plan |
| "user personas", "who is this for", "target user", "jobs-to-be-done", "analytics plan", "success metrics", "what should we measure", "define our users" | user-personas-behavior |
| "write a spec", "requirements for", "SRS for", "TSD for", "define requirements", "functional requirements", "system requirements", "what must the system do" | technical-specification |
| "is this feasible", "can we build", "evaluate this technically", "PoC for", "proof of concept", "technical feasibility", "assess this idea" | technical-feasibility-study |
| "user flow", "UX flow", "screen flow", "information architecture", "user journey map", "UI states", "what screens do we need", "how does the user move through" | ux-flow-specification |
| "design system for", "style guide for", "visual tokens for", "UI specification", "design.md", "design-system.md", "color palette", "typography scale" | design-system-specification |
| "document the architecture", "system architecture for", "SAD for", "C4 diagram", "how does this system work", "architecture overview", "system design" | system-architecture-document |
| "document this decision", "write an ADR", "record this decision", "why did we choose", "architecture decision", "we decided to use" | architecture-decision-record |
| "database design", "schema for", "data model for", "ERD for", "database schema", "data dictionary", "table design" | database-design-document |
| "design this API", "API spec for", "API contract", "OpenAPI for", "REST API design", "GraphQL schema", "define the endpoints" | api-design-document |
| "access control", "permissions for", "RBAC", "admin roles", "role matrix", "who can do what", "audit logging", "privilege levels", "break-glass access" | admin-access-control-specification |
| "design this feature", "technical design for", "design doc for", "TDD for", "how do we build", "engineering design", "technical approach" | technical-blueprint |
| "threat model", "security review", "STRIDE analysis", "security risks of", "what can go wrong security", "attack surface" | security-threat-model |
| "test strategy for", "QA plan for", "testing framework for", "test cases for", "test-strategy.md", "how do we test" | test-strategy-document |
| "implementation plan", "build order", "build sequence", "what order to build", "phase gates", "technical build sequence", "dependency-driven phases" | implementation-plan |
| "deployment plan", "release plan", "how do we deploy", "rollout plan", "blue-green", "canary deployment", "go-live plan" | deployment-plan |
| "SLO for", "error budget", "reliability target", "SLI definition", "burn-rate alert", "uptime target", "service level objective" | slo-error-budget-document |
| "write a runbook", "operations manual", "on-call guide", "how to operate", "ops runbook", "playbook for" | technical-runbook |
| "disaster recovery", "DR plan", "RTO", "RPO", "backup strategy", "failover plan", "business continuity", "what if the server dies" | disaster-recovery-plan |
| "post-mortem", "postmortem", "incident report", "RCA for", "root cause", "blameless review", "what went wrong" | incident-postmortem |
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 · 75 lines · 0 tokens per session scan A a278ac9c2f54
CLAUDE is an agent published in the GitHub repository fattain-naime/engineering-docs (4 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,715 tokens. 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
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.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.