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 skills add dbhq-uk/vela-skill --skill velagit clone --depth 1 https://github.com/dbhq-uk/vela-skillWrote 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/skills/dbhq-uk/vela-skill/vela)<a href="https://agentmods.dev/skills/dbhq-uk/vela-skill/vela"><img src="https://agentmods.dev/badge/skills/dbhq-uk/vela-skill/vela/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/skills/dbhq-uk/vela-skill/vela"><img src="https://agentmods.dev/badge/skills/dbhq-uk/vela-skill/vela.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00213 | $0.01471 |
| Opus 5.5 | $0.00085 | $0.00588 |
| Sonnet 5.5 | $0.00043 | $0.00294 |
| Haiku 4.5 | $0.00021 | $0.00147 |
Grade A, and why
vela 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vela
Compiler-exact code search over a SCIP index. .NET answers come from Roslyn, other languages from their own indexers' .scip files. It never writes to the repository.
Which tool
- grep when the name is distinctive. It is free and needs no index.
- The LSP tool, where your host has one, for code you have just edited. It stays live, where vela needs a re-index, which takes minutes on a large solution.
- vela for:
- ordinary names (
Name,Status,Id), where grep is mostly noise and vela reports when a name is ambiguous - references from
.cshtmland.razorfiles - callers, implementations, and what a change touches
- a survey of a clean tree before a change
- ordinary names (
- Not vela in a repository with no .NET and no
.scipto import.
Steps
0. Check the command is installed
command -v vela
Plugin and skills.sh installs copy this file, not the command. If it prints nothing, tell the user rather than quietly falling back to grep. vela needs:
- the .NET SDK 10.0 or newer
- the tool itself: clone
https://github.com/dbhq-uk/vela-skilland run./install.sh ~/.dotnet/toolsonPATH
1. Build the index
vela does not restore packages. Run dotnet restore first if the solution has never been built.
vela index
vela uses the solution vela.json names, or else the only .sln or .slnx here or in the nearest directory above, up to the repository root. If it cannot pick one, pass --solution <path> to every command.
Indexing costs about what a build costs. Re-index after every code change: once a watched file is newer than the index, answers carry the stale banner. vela index --incremental rebuilds only what changed. Index without it before you delete or rename anything.
If a project fails to load or compile, vela says so, and whatever depended on it is missing.
2. Add other languages
vela import path/to/index.scip # first time
vela import --replace path/to/index.scip # after re-running that indexer
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.
- 1mo ago Changed · -12 tokens per session 625e8d8eecc6
- 1mo ago Changed · -35 lines · +225 tokens per session 22c86c32e6f9
- 1mo ago Changed · -164 tokens per session dc39e0ddbb53
- 2mo ago First seen · 130 lines · 164 tokens per session scan A 74ec4dd55c7e
vela is a skill published in the GitHub repository dbhq-uk/vela-skill (6 stars, last pushed 11d ago), licensed MIT. It adds 213 tokens to every session and 1,471 once invoked, about $0.0009 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 2026-08-31.
vela compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| veladbhq-uk/vela-skill | Skill | 6 | 11d ago | MIT | A | 213 | Claude Code |
| mapsuiznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 107 | Claude Code, Codex |
| dotnet-performanceAttemainio/dotnet-toolkit | Skill | 2 | 1mo ago | MIT | A | 376 | Claude Code |
| dotnet-reviewAttemainio/dotnet-toolkit | Skill | 2 | 1mo ago | MIT | A | 218 | Claude Code |
| dotnet-exploreAttemainio/dotnet-toolkit | Skill | 2 | 1mo ago | MIT | A | 104 | Claude Code |
| dotnet-analyzer-code-intelligenceCartapenaBark/DotNetAnalyzer | Skill | 2 | 6mo ago | MIT | A | 226 | Claude Code |
| opentelemetry-net-instrumentationAaronontheweb/dotnet-skills | Skill | 1.3k | 9d ago | MIT | A | 56 | Claude Code |