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/evyasys-software-solutions/evyagovernance/claude-mdgit clone --depth 1 https://github.com/Evyasys-Software-Solutions/EvyaGovernanceWhat 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 | $0.04426 | $0.04426 |
| Opus 5 | $0.02213 | $0.02213 |
| Sonnet 5 | $0.00885 | $0.00885 |
| Haiku 4.5 | $0.00443 | $0.00443 |
Grade A, and why
EvyaGovernance CLAUDE.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.parse How it starts
The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EvyaGovernance — Claude Code Project Standards
This file is the authoritative reference for all code generation, review, and modification in this repository. Read it completely before writing a single line.
1. Project Overview
EvyaGovernance is an AI-assisted SDLC delivery pipeline built by Evyasys Software Solutions. It integrates Claude Code skills with Azure DevOps and Microsoft Teams to automate the full story lifecycle: Create → Subtask → StartDev → ReviewDev → FinishDev → StartQA → FinishQA.
Architecture layers (top to bottom)
Claude Agent (AI prompt + agent result)
↓
skills/evyasys-*/hooks.js orchestration — save artefacts, confirm, call integrations
↓
scripts/lib/ utilities — config, ado-map, dryrun, markdown-to-html
↓
scripts/integrations/ external service clients — azure_devops, teams_webhook
↓
.evyasys/ per-project runtime state — board/, .ado-map.json, project.yaml
↓
Azure DevOps API / Teams webhook external systems
Never cross layers upward. A lib utility must not import a hook. An integration must not import another integration. State flows downward only.
2. Folder Structure
/
├── .ai/ AI control plane (Git-backed, shared with team)
│ ├── core/ Quality gates, output contract, human confirmation rules
│ ├── rules/ Coding and naming standards applied by every workflow
│ ├── workflows/ Per-command: PROMPT.md, AGENT.md, CHECKLIST.md, templates
│ └── manifest.yaml Plugin defaults (work-item types, dry-run flag)
├── .evyasys/ Per-project runtime (generated, committed)
│ ├── board/ Artefacts: epics/{id}/stories/{id}/ or stories/{id}/
│ ├── .ado-map.json Evyasys ID → ADO numeric ID + directory mapping
│ └── project.yaml Project config: org, ADO project, Teams webhook
├── commands/ User-facing command definitions (PascalCase.md)
├── scripts/
│ ├── lib/ Reusable utilities (kebab-case.js / snake_case.py)
│ └── integrations/ External API clients (azure_devops.js/.py, teams_webhook.js)
└── skills/
└── evyasys-<command>/ One folder per skill: hooks.js + SKILL.md
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 · 481 lines · 4,426 tokens per session scan A de945c09cb82
EvyaGovernance CLAUDE.md is an instructions file published in the GitHub repository Evyasys-Software-Solutions/EvyaGovernance (7 stars, last pushed 19d ago), licensed MIT. It adds 4,426 tokens to every session, about $0.0221 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
DeepSpeed AGENTS.md
AGENTS.md instructions for deepspeedai/DeepSpeed, covering deepspeed project rules, commit & ci requirements, code change discipline, tool caveats and edit tool auto-formatter.
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
packmind packmind-rest-api-endpoint-design.instructions.md
Instructions for PackmindHub/packmind: Conventions for designing REST API endpoints that are predictable, self-documenting, and aligned with distinct business actions. Favors dedicated action endpoints over generic status updates, and rout... .
cli-continues security.instructions.md
Instructions for yigitkonur/cli-continues, covering security review guidelines — core utilities, command injection prevention (resume.ts), forward flag security (forward-flags.ts), handoff output safety (markdown.ts) and general.
sdlc-quality copilot-instructions.md
Instructions for zircote-plugins/sdlc-quality, covering copilot instructions for sdlc plugin, project overview, repository structure, key conventions and rfc 2119 terminology.
swttch CLAUDE.md
Claude Code instructions for Swttch/swttch, covering claude.md, 프로젝트 개요, ★ 핵심 원칙 — cli 동등성 & 공식 지원 비의존 (최우선, 위반 금지), 아키텍처 and 구현 기준.