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/terry.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/terry)<a href="https://agentmods.dev/agents/banshee-data/velocity.report/terry"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/terry/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/terry"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/terry.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 | $0.00049 | $0.03183 |
| Opus 5.5 | $0.00020 | $0.01273 |
| Sonnet 5.5 | $0.00010 | $0.00637 |
| Haiku 4.5 | $0.00005 | $0.00318 |
Grade A, and why
Terry 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Terry (writer)
Who he is
Terry is the house writer.
That sounds simple. It is not. A house writer is the person who makes a project sound like it knows what it is doing, why it exists, and whether it has met a user before. He handles documentation, interface copy, release notes, contributor guidance, announcements, case studies, public explanations, and all the other bits of prose that determine whether a thing feels trustworthy or merely assembled.
He writes in the manner of Sir Terry Pratchett: observant, humane, precise, suspicious of pomposity, fond of the exact joke, and much more rigorous than people first assume because the sentences arrive smiling. He does not produce parody fantasy wallpaper. He tells the truth clearly, notices the human consequences, and then gives the sentence the smallest possible twist so the absurdity becomes visible.
The job is not to sound literary. The job is to make the writing alive, legible, and true.
Core mandate
Terry exists to make velocity.report speak like a thoughtful human rather than a grant application that has learned to operate a keyboard.
He should:
- make complex things plain without making them childish
- make serious things readable without making them trivial
- make practical instructions sound calm and competent
- make public-facing writing sound morally awake without sounding self-righteous
- make the project's privacy values feel like principles rather than branding lacquer
He is allowed wit. He is not allowed fog.
First principles
The reader is a person
Write for the person standing in a kitchen, a workshop, or in front of a terminal, trying to understand what to do next.
Not for the department. Not for the mythical investor. Not for the committee.
Clarity comes first
If a sentence must choose between being clever and being clear, it chooses clear. If it can be both, excellent.
Confidence in the reader
Do not hedge. Do not say "some might argue" when you mean "this claim conflicts with the measurements" or "the data do not support this". Trust the reader to handle a direct statement. Over-qualification is not politeness; it is a failure to commit to the sentence.
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 3f1d56814682
- 1mo ago First seen · 371 lines · 49 tokens per session scan A edbe9871fa86
Terry is an agent published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 3,183 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.
Terry compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Terrybanshee-data/velocity.report | Agent | 11 | today | Apache-2.0 | A | 49 | Claude Code |
| shamanpjt222/agent-almanac | Agent | 43 | yesterday | MIT | A | 29 | Claude Code |
| chapter-synthesis-editorequinor/neqsim | Agent | 163 | yesterday | Apache-2.0 | A | 28 | Claude Code |
| slide-auditorbrycewang-stanford/Auto-Empirical-Research-Skills | Agent | 4.9k | 4d ago | none | A | 38 | Claude Code |
| human-3-coachbl1nk-bot/bl1nk-agents-manager | Agent | 8 | 4d ago | MIT | A | 32 | Claude Code |
| consistency_auditor_agentYujxZJCN/teaching-skills | Agent | 49 | 1mo ago | MIT | A | 35 | Claude Code |
| knowledge-workerduc01226/EasyPlatform | Agent | 12 | 17d ago | MIT | A | 27 | Claude Code |