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 instructions/shangyankeji/super-dev/agents-mdgit clone --depth 1 https://github.com/shangyankeji/super-devWrote 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/instructions/shangyankeji/super-dev/agents-md)<a href="https://agentmods.dev/instructions/shangyankeji/super-dev/agents-md"><img src="https://agentmods.dev/badge/instructions/shangyankeji/super-dev/agents-md.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 | $0.06466 | $0.06466 |
| Opus 5 | $0.03233 | $0.03233 |
| Sonnet 5 | $0.01293 | $0.01293 |
| Haiku 4.5 | $0.00647 | $0.00647 |
Grade A, and why
super-dev AGENTS.md 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 3d 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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Overview
Super Dev is a Python CLI tool (v2.4.0) that orchestrates AI-driven development pipelines inside host environments (e.g., Claude Code). It provides governance, quality gates, and audit artifacts for commercial-grade software delivery. It is NOT an independent AI agent — it's a governance layer that runs inside a host's coding environment.
Project Structure & Module Organization
super_dev/
cli.py # Main CLI entry point (~298k lines), composed via mixins
cli_parser_mixin.py # argparse command definitions
cli_analysis_mixin.py # analysis subcommands
cli_governance_mixin.py # governance/enforcement subcommands
cli_host_ops_mixin.py # host tool operations (~227k lines)
cli_host_report_renderers.py # host report rendering helpers
cli_experience_mixin.py # UX enhancements
cli_deploy_runtime_mixin.py # deployment/runtime commands
cli_release_quality_mixin.py # release & quality commands
cli_spec_mixin.py # spec management commands
branding.py # CLI branding and visual identity
catalogs.py # catalog data definitions
error_handler.py # centralized error handling
exceptions.py # custom exception classes
i18n.py # internationalization support
guard.py # guard/safety checks
host_adapters.py # host environment adapters
host_registry.py # host registration/discovery
merge_safety.py # merge safety checks
retry.py # retry utilities
runtime_evidence.py # runtime evidence collection
seeai_design_system.py # SEEAI design system definitions
seeai_smoke_scenarios.py # SEEAI smoke test scenarios
sequential_thinking.py # sequential thinking utilities
session_checkpoint.py # session checkpoint management
workflow_contract.py # workflow contract definitions
orchestrator/ # Pipeline engine, governance, quality gates
engine.py # main pipeline engine driving phase transitions
governance.py # governance policy enforcement
quality.py # quality gate evaluation
knowledge.py / knowledge_pusher.py # knowledge injection into pipeline stages
overseer.py # Overseer agent for plan-execute orchestration
plan_executor.py # Plan-Execute engine for Claude-Codex hybrid mode
experts.py # expert persona management in pipeline
context_compact.py # context compaction for long pipelines
contracts.py # pipeline contract definitions
telemetry.py # pipeline telemetry and metrics
creators/ # Document, prompt, frontend, and backend generators
document_generator.py # PRD, architecture, UIUX document generation
document_generator_content_mixin.py # document content generation mixin
prompt_generator.py / prompt_templates.py / prompt_sections.py # LLM prompts
frontend_builder.py # frontend implementation playbooks
implementation_builder.py # backend implementation references
spec_builder.py # spec generation from documents
adr_generator.py # Architecture Decision Record generation
api_contract.py # API contract generation
component_scaffold.py # component implementation references
nextjs_scaffold.py # Next.js implementation references
requirement_parser.py # requirement parsing utilities
task_executor.py # task execution within creator pipeline
creator.py # base creator class
compact_template.py # compact template utilities
design/ # Design intelligence (aesthetics, UX, charts, codegen)
ui_intelligence.py # UI design intelligence engine
aesthetics.py # visual aesthetics analysis
ux_guide.py # UX guidance rules
engine.py # design engine orchestration
generator.py # design artifact generation
codegen.py # design-to-code generation
charts.py # chart design generation
landing.py # landing page design
tech_stack.py # tech stack design decisions
tokens.py # design token management
reviewers/ # Code review, red-team, quality gate, UI review
quality_gate.py # quality threshold enforcement (default: 90)
quality_advisor.py # quality improvement suggestions
redteam.py # security red-team analysis
code_review.py # automated code review
ui_review.py # UI compliance review
validation_rules.py # configurable validation rules engine
external_reviews.py # external review integrations
review_agents.py # review agent definitions
rules/ # validation rule definitions
enforcement/ # File-level validation and pre-coding checks
validation.py # file-level validation (no emoji icons, color tokens, etc.)
pre_code_gate.py # pre-coding checks
host_hooks.py # hook integration with host tools
deployers/ # Delivery packaging, CI/CD, deployment rehearsals
delivery.py # delivery packaging
cicd.py # CI/CD pipeline generation
rehearsal.py / rehearsal_runner.py # deployment rehearsal definitions and execution
migration.py # deployment migration utilities
protocols/ # Shared protocol definitions
a2a.py # agent-to-agent protocol
output_schemas.py # output schema definitions
integrations/ # External tool integration manager
manager.py # integration lifecycle management
manager_content_mixin.py # integration manager content mixin
install_manifest.py # install manifest tracking
skills/ # Skill definitions for host environments
manager.py # skill lifecycle management
skill_template.py # skill template generation
web/ # FastAPI-based web interface
api.py # main API application
helpers.py # API helper functions
rate_limit.py # API rate limiting
routers/ # API route modules
frontend/ # web frontend assets
config/ # Configuration management
experts/ # Expert persona definitions (PM, Architect, etc.)
hooks/ # Host tool hook integration
analyzer/ # Code and project analysis utilities
memory/ # Session memory management
metrics/ # Metrics collection and reporting
policy/ # Policy engine for governance rules
session/ # Session management
specs/ # Spec management and templates
rules/ # Rule definitions
data/ # Static data files
utils/ # Shared utility functions (logger, structured_logging)
templates/ # Jinja/data templates
knowledge/ # Curated domain knowledge base (28 categories)
tests/ # Test suites (unit, integration, e2e, benchmark)
scripts/ # Build/release/utility scripts
output/ # Generated pipeline artifacts (PRD, specs, research)
.super-dev/ # Session state and workflow tracking
super-dev-website/ # Project website source
templates/ # Project implementation/reference templates
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.
- 3d ago First seen · 500 lines · 6,466 tokens per session scan A 6ca915290216
super-dev AGENTS.md is an instructions file published in the GitHub repository shangyankeji/super-dev (274 stars, last pushed 2mo ago), licensed MIT. It adds 6,466 tokens to every session, about $0.0323 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 instructions, from other repositories
pg-aiguide CLAUDE.md
Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands, code style guidelines and python (ingest/).
map-framework CLAUDE.md
Instructions for azalio/map-framework, covering map framework (mapify-cli) — agent instructions, what this repo is, critical invariant: template single-source render, skill catalog invariant and how to work in this repo.
MonkeyCode AGENTS.md
AGENTS.md instructions for chaitin/MonkeyCode, covering git 提交与推送规则, ohmydesign-tmp 例外, 启动 monkeycode debug app（开发与测试）, 1. 编译 agent（必须用最新功能分支代码） and 2. 启动 debug app（ui-next 热加载）.
claude-cost-optimizer CLAUDE.md
Claude Code instructions for Sagargupta16/claude-cost-optimizer, covering claude.md - claude-cost-optimizer, purpose, file structure, writing conventions and python tools.
easy-cheese python.instructions.md
Instructions for paulnsorensen/easy-cheese, covering hard rules, what to flag and what not to flag.
r-code AGENTS.md
Instructions for foritin/r-code, covering agents.md — r-code 仓库开发规约, 工具使用速查（避免低级报错）, 通则 and 本仓库技术栈.