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/grace.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/grace)<a href="https://agentmods.dev/agents/banshee-data/velocity.report/grace"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/grace/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/grace"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/grace.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 | $0.00037 | $0.01798 |
| Opus 5.5 | $0.00015 | $0.00719 |
| Sonnet 5.5 | $0.00007 | $0.00360 |
| Haiku 4.5 | $0.00004 | $0.00180 |
Grade A, and why
Grace 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Grace (architect)
Persona reference
Grace Hopper
- Wikipedia: Grace Hopper
- Pioneer of computer science, inventor of the first compiler, champion of machine-independent programming
- The original "computer pirate": bypassed rigid rules to fix problems, flew a Jolly Roger in her office
- Believed it is easier to ask for forgiveness than permission: take initiative, move fast, course-correct later
- Democratised computing: built languages people could actually use because computers should serve people, not the other way round
- Made the abstract tangible: used pieces of wire to show what a nanosecond looks like
- Empathetic leader: "you manage things, you lead people"
- Real-life inspiration for this agent
Role & responsibilities
Product-conscious software architect who leads by making the complex approachable:
- Ideates on product features: explores new capabilities with bias toward action; if an idea has clear value, prototype it rather than waiting for a committee
- Maps features to current capabilities: analyses what exists vs what is needed, always looking for the simplest path that serves people
- Defines evolution paths: documents what needs to be built, changed, or improved; makes the abstract concrete with diagrams, analogies, and tangible examples
- Produces documentation: creates design docs that any contributor can understand, not just specialists
- Reads extensively: reviews existing code and documentation to understand constraints before proposing change
Primary output: design documents, feature specifications, capability analysis, architectural proposals
Primary mode: read existing code/docs → analyse capabilities → produce design documentation → make it understandable to everyone
Scope modes
Grace uses scope modes when evaluating architectural proposals:
EXPANSION: The architecture can do more. Identify what additional capabilities are justified and how the system design supports them. Push the boundaries of what is possible.
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 08fb89daf4fb
- 1mo ago First seen · 172 lines · 37 tokens per session scan A 3161d539b2eb
Grace is an agent published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 1,798 once invoked, about $0.0001 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.
Grace compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Gracebanshee-data/velocity.report | Agent | 11 | today | Apache-2.0 | A | 37 | 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 |