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.
git clone --depth 1 https://github.com/Evyasys-Software-Solutions/EvyaGovernanceWrote 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/commands/evyasys-software-solutions/evyagovernance/createstory)<a href="https://agentmods.dev/commands/evyasys-software-solutions/evyagovernance/createstory"><img src="https://agentmods.dev/badge/commands/evyasys-software-solutions/evyagovernance/createstory.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 5.1 | $0.00064 | $0.00980 |
| Opus 5 | $0.00032 | $0.00490 |
| Sonnet 5 | $0.00013 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade B, and why
CreateStory scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
macOS / Linux (Bash): `EVYA_AI=$(find "$HOME/.claude/plugins" -maxdepth 6 -type d -name ".ai" 2>/dev/null | grep -i "EvyaGovernance" | head -1); [ -z "$EVYA_AI" ] && EVYA_AI=".ai"; echo "$EVYA_AI"` How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /evyasys:CreateStory.
Step 0 — Input Gate ⛔ HARD GATE
First — find the plugin's installed workflow directory:
macOS / Linux (Bash): EVYA_AI=$(find "$HOME/.claude/plugins" -maxdepth 6 -type d -name ".ai" 2>/dev/null | grep -i "EvyaGovernance" | head -1); [ -z "$EVYA_AI" ] && EVYA_AI=".ai"; echo "$EVYA_AI"
Windows (PowerShell): $EVYA_AI = (Get-ChildItem "$env:USERPROFILE\.claude\plugins" -Recurse -Directory -Filter ".ai" -ErrorAction SilentlyContinue | Where-Object { $_.FullName -like '*EvyaGovernance*' } | Select-Object -First 1 -ExpandProperty FullName); if (-not $EVYA_AI) { $EVYA_AI = ".ai" }; Write-Output $EVYA_AI
Read the full workflow from <plugin-ai>/workflows/create-story/PROMPT.md (use the path printed above instead of .ai). If the file is not found at the plugin path, fall back to .ai/workflows/create-story/PROMPT.md.
The very first thing you do is present the user with two options and wait:
How would you like to provide the story requirements?
(A) Describe it here — I'll guide you through structured questions one at a time.
(B) Reference document — provide a path to a requirements doc, transcript, wireframe, or written brief. I'll analyse it as BA + Architect + Scope before asking only the gaps that are missing.
Do not read any project files, detect any epics, or load any context until the user responds.
Path A — Describe here
Follow PROMPT.md Steps 1–6: load context → Epic resolution (Gate 1) → clarifying Q&A → story plan (Gate 2) → draft all → output blocks.
Path B — Reference document
- Ask for the file path and wait.
- Read every file provided.
- Run BA + Architect deep analysis (four perspectives: Business, Architecture, Quality, Scope Decomposition — cite document text for each finding).
- Ask only blocking Q&A questions (one at a time, with reason stated).
- Archive the document to
.evyasys/board/referencedoc/{YYYY-MM-DD}/— append the full analysis + Q&A to the archived copy. - Notify the user of the archive location.
- Continue to PROMPT.md Steps 1–6.
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.
- 8d ago First seen · 70 lines · 64 tokens per session scan B 9ed3ab985142
CreateStory is a command published in the GitHub repository Evyasys-Software-Solutions/EvyaGovernance (7 stars, last pushed 26d ago), licensed MIT. It adds 64 tokens to every session and 980 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
create-new-package-in-monorepo
Create a new buildable TypeScript package in the Packmind monorepo using Nx tools and configure it for use across applications.
CLAUDE
The "commands" domain — multi-step coding commands, their versions, and their deployment.
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
work
Execute Memory Bank workflow modes from pipeline.yaml — existing plan/spec execution by default, optional full-cycle requirements→plan→implementation→review flows.
sdd
Generate a Kiro-style spec triple — specs/ /{requirements,design,tasks}.md.