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 bravew/trove --skill trove-verifygit clone --depth 1 https://github.com/bravew/troveWrote 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/bravew/trove/trove-verify)<a href="https://agentmods.dev/skills/bravew/trove/trove-verify"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-verify/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/bravew/trove/trove-verify"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-verify.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 | $0.00023 | $0.00439 |
| Opus 5.5 | $0.00009 | $0.00176 |
| Sonnet 5.5 | $0.00005 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
trove-verify 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.
What it actually says
Session Init
This skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.
If a sibling skill in this plugin matches the request more directly, defer to it. See AGENTS.md (or docs/routing.md in the marketplace) for the per-plugin routing index.
trove-verify
Before claiming done: run the tests, reread the diff, list the unverified assumptions.
Verify the real thing
"It compiles", "the build passed", or "the screenshot rendered" is not verification of behavior. Check the actual artifact the change was supposed to affect: the running endpoint returns the right body, the rendered UI shows the right pixels, the migration moved the right row count. Name what you checked.
When a check will be re-run, script it as a deterministic, re-runnable comparison (old value vs new value) rather than a one-off glance. When work was delegated to a sub-agent, trust the git diff and the artifacts it produced — never its prose summary of what it did.
Self-check
- Run the most relevant test, lint, typecheck, build, or manual inspection.
- Reread the touched diff for unintended churn and user-owned changes.
- Confirm generated artifacts are fresh when generators are involved.
- Name any verification that could not run and why.
Decision Gate: completion claim
Context: A completion claim is only useful if it says what was actually proven. Question: Is the requested outcome verified? Options:
- A. Yes - summarize changes and verification.
- B. Partially - summarize changes and call out the gap.
- C. No - keep working or ask for the missing input. Default: C, because unverified work is not complete.
Output
Use concise prose: what changed, what passed, and what remains unverified.
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 First seen · 44 lines · 23 tokens per session scan A 00ddfeacc4a6
trove-verify is a skill published in the GitHub repository bravew/trove (10 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 439 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 2026-09-11.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.