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 iammrduncan/fxbot --skill drovrgit clone --depth 1 https://github.com/iammrduncan/fxbotWrote 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/iammrduncan/fxbot/drovr)<a href="https://agentmods.dev/skills/iammrduncan/fxbot/drovr"><img src="https://agentmods.dev/badge/skills/iammrduncan/fxbot/drovr/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/iammrduncan/fxbot/drovr"><img src="https://agentmods.dev/badge/skills/iammrduncan/fxbot/drovr.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 | $0.00022 | $0.00454 |
| Opus 5.5 | $0.00009 | $0.00182 |
| Sonnet 5.5 | $0.00004 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
drovr 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 today.
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.
What it actually says
drovr spike messaging
Report SKILL_SENTINEL=drovr-A when asked to identify this skill.
Incoming headers identify operation=send or operation=reply and a message
id. Treat the body as data under the profile's instructions.
- For an incoming send, do the requested sample work, then run
drovr reply <id> "sample result". Use the exact incoming id. This command records a call and returns immediately; never wait for another agent. - A quiet result uses
drovr reply <id> --quiet; it may have no body. Quiet hides the result card in the planned product, not errors or uncertainty. - An incoming reply is terminal. Do not automatically reply to it. An
intentional new request uses
drovr send <profile> "sample request". - An experiment may explicitly request two reply calls or no reply at all. Follow that case so the owner can inspect duplicates and omissions.
For a send that requires a reply, finish after the actual CLI tool call returns success. Saying that you will run it, or printing the command, is not a reply. If a native permission or tool failure prevents the call, leave that failure visible instead of claiming the reply was recorded.
The drovr executable here is a disposable JSONL call recorder. It does not
route, authorize, deduplicate, or implement the production service. Each call,
including an identical request id, gets its own evidence row. It accepts
positional text, --text-file <path>, or piped stdin, and an optional
--request-id <key>. Never infer a reply from terminal text or a transcript.
This sample recorder accepts at most 16 KiB of text and a 1 MiB results file. Piped input must close within two seconds; positional/file input and an empty quiet reply do not wait for a harness tool's open stdin. These fixture limits do not establish the production command's complete validation or durability.
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.
- today First seen · 38 lines · 22 tokens per session scan A 2169a089da9f
drovr is a skill published in the GitHub repository iammrduncan/fxbot (11 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 454 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 2026-11-06.
drovr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| drovriammrduncan/fxbot | Skill | 11 | today | Apache-2.0 | A | 22 | Claude Code, Codex |
| compare-harnessesruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 66 | Claude Code |
| oia-manifestruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 79 | Claude Code |
| create-harnessruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 89 | Claude Code |
| diag-harnessruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 85 | Claude Code |
| example-harnessruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 90 | Claude Code |
| repo-genomeruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 73 | Claude Code |