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/deliver)<a href="https://agentmods.dev/commands/evyasys-software-solutions/evyagovernance/deliver"><img src="https://agentmods.dev/badge/commands/evyasys-software-solutions/evyagovernance/deliver/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/commands/evyasys-software-solutions/evyagovernance/deliver"><img src="https://agentmods.dev/badge/commands/evyasys-software-solutions/evyagovernance/deliver.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 | $0.00086 | $0.00513 |
| Opus 5 | $0.00043 | $0.00257 |
| Sonnet 5 | $0.00017 | $0.00103 |
| Haiku 4.5 | $0.00009 | $0.00051 |
Grade B, and why
Deliver scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
EVYA_AI=$(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" What it actually says
You are running /evyasys:Deliver $ARGUMENTS.
Step 0 — Load workflow
First — find the plugin's installed workflow directory (do this before any file read):
macOS / Linux — run via Bash:
EVYA_AI=$(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 — run via 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
Use the printed path in place of .ai for every workflow file read below.
If a file is not found at the plugin path (older install), fall back to the same path under .ai/.
Load these files from <plugin-ai>/workflows/deliver/:
AGENT.md— your role, mandate, and speed contractPROMPT.md— the 10-phase workflow with the 3 gatesCHECKLIST.md— the self-review checklist
Then follow the workflow in PROMPT.md exactly. Do not skip Phase 0 batch load —
it is the reason the whole run stays fast.
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.
- 9d ago First seen · 34 lines · 86 tokens per session scan B d04dde69d5b6
Deliver is a command published in the GitHub repository Evyasys-Software-Solutions/EvyaGovernance (7 stars, last pushed 27d ago), licensed MIT. It adds 86 tokens to every session and 513 once invoked, about $0.0004 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
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
spec
Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.