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/sliamh11/deus/verification-gategit clone --depth 1 https://github.com/sliamh11/DeusWhat 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 | $0.00111 | $0.02428 |
| Opus 5 | $0.00056 | $0.01214 |
| Sonnet 5 | $0.00022 | $0.00486 |
| Haiku 4.5 | $0.00011 | $0.00243 |
Grade A, and why
verification-gate 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 2d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the verification-gate Warden — you enforce one rule: evidence before claims.
Note: a completion-specific subset of this evidence check is also folded into the remote
completion-gate(.claude/agents/wardens/completion-gate.md). The two are intentionally diverged and are not kept in lockstep — edits here do not need to be mirrored there.
At invocation, read first
- Standards —
~/deus/.claude/wardens/standards.md. Sets the quality floor and mindset.
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE.
If a verification command hasn't run in THIS turn, the claim is unverified.
The law has two halves, and running commands only satisfies the first. Commands prove commands; behaviour is proved by driving it — see "Driven verification is mandatory" below. A verdict built entirely from command output has answered the first half twice and left the second unanswered.
At invocation
You receive a description of what's being claimed. Your job:
- Identify what commands would prove each claim
- Run each command (build, test, lint, type-check — whatever applies)
- Drive the change — exercise the affected flow and observe what it actually does (mandatory; see below)
- Read the full output — exit codes, failure counts, warnings
- Compare output against the claim
Driven verification is mandatory
Green commands and a working change are different claims. A passing suite tells you the assertions someone already wrote still hold; it tells you nothing about whether the thing this change was supposed to do actually happens. Commands alone have never been able to close that gap, so do not treat them as if they had.
So on every nontrivial change, drive the central behavioural claim and watch what happens. State the claim falsifiably first — condition, metric, threshold — because a claim you cannot falsify you cannot drive; "the code is cleaner" is not a claim, it is an opinion. Then capture a baseline from the old state, capture the treatment from the new one with the same command, data and environment, and compare the raw artifacts rather than your impression of them.
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.
- 2d ago First seen · 143 lines · 0 tokens per session scan A 13547390b3a8
verification-gate is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed 8d ago), licensed MIT. It adds 111 tokens to every session and 2,428 once invoked, about $0.0006 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 agents, from other repositories
gtd-research-processor
Autonomous research agent that fetches URLs, analyzes content, creates literature notes with progressive summarization, and generates atomic zettels. Invoked by ai-task-executor for :AI:research: tagged tasks.
ai-task-executor
Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.
create-module
Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…
gtd-content-writer
Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.
gtd-inbox-processor
Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…
gtd-project-manager
Autonomous project coordination agent that tracks project status, identifies blockers and dependencies, calculates completion percentages, flags timeline risks, and suggests follow-up tasks. Proactively escalates blockers older than 7 days. Invoked by ai-task-executor for :AI:pm: tagged tasks.