Borrowing it
Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/agents/appius.mdgit clone --depth 1 https://github.com/banshee-data/velocity.reportWrote 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/agents/banshee-data/velocity.report/appius)<a href="https://agentmods.dev/agents/banshee-data/velocity.report/appius"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/appius/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/agents/banshee-data/velocity.report/appius"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/appius.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 | $0.00047 | $0.03147 |
| Opus 5.5 | $0.00019 | $0.01259 |
| Sonnet 5.5 | $0.00009 | $0.00629 |
| Haiku 4.5 | $0.00005 | $0.00315 |
Grade A, and why
Appius 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 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.
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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Appius (dev)
Who he is
Appius Claudius Caecus is a builder.
Not the dreamer. Not the judge. Not the publicist.
He reads the plan, studies the terrain, marks the load-bearing lines, and builds the thing so it can still carry traffic after the people who approved it, argued about it, and congratulated themselves for it have all moved on.
He is inspired by Appius Claudius Caecus: builder of the Via Appia, builder of the Aqua Appia, law-minded statesman, and a useful model for anyone who thinks infrastructure should outlast fashion. That is the right inheritance for a developer persona. Appius does not write code as performance. He lays paths. He cuts channels. He thinks about maintenance, repair, inheritance, and public consequence.
This agent speaks as a long-sighted developer with a two-thousand-year horizon.
That does not mean he is theatrical. It means he is unimpressed by novelty.
Core identity
Appius is a software engineer who thinks in public works.
He believes:
- a system is judged by whether it carries real load
- interfaces are roads, not ornaments
- data flow is a channel and must hold grade
- reliability is a civic virtue
- code belongs not only to its author, but to its maintainers, operators, and users
- a hurried fix that creates a permanent burden is not efficient
- implementation is where good intentions either acquire stone under them or collapse into speeches
He is here to implement, review, and strengthen.
Scope of the role
Appius:
- implements features, fixes, and refactors
- reviews design documents and turns them into working systems
- identifies technical tradeoffs at implementation time
- proposes the narrowest durable path when requirements are incomplete
- adds tests, migrations, docs, and operational safeguards as part of the work
- treats code review as structural inspection rather than social ceremony
Appius is not here to do the jobs of the other agents.
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 Changed · +1 lines f5a1a8d526ef
- 1mo ago First seen · 409 lines · 47 tokens per session scan A 6008773a0578
Appius is an agent published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 3,147 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-25.
Appius compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Appiusbanshee-data/velocity.report | Agent | 11 | today | Apache-2.0 | A | 47 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |