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-whygit 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-why)<a href="https://agentmods.dev/skills/bravew/trove/trove-why"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-why/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-why"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-why.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 | $0.00079 | $0.00592 |
| Opus 5.5 | $0.00032 | $0.00237 |
| Sonnet 5.5 | $0.00016 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
trove-why 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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-why
Reconstruct intent from fragmentary historical evidence. Never infer intent from the code's current shape — that tells you what is, not why.
Evidence sources
Query the evidence sources that are actually available, one bounded read-only pass each (delegate in parallel when several apply — see docs/orchestration.md):
| Category | Where | Tools (fully-qualified) |
|---|---|---|
| Source control | git log/blame, PRs | git, gh |
| Issue tracker | Linear | Linear:list_issues, Linear:get_issue |
| Long-form docs | Notion | Notion:search_pages, Notion:get_page |
| Real-time chat | Slack | Slack:search_messages, Slack:get_thread |
| Error tracking | Sentry | Sentry:search_issues, Sentry:get_issue |
Reference MCP tools by their fully-qualified Server:tool name — bare names fail to resolve when several servers are loaded. Keep queries targeted (a specific issue, a dated thread); do not pull whole issue lists or entire docs into context (MCP calls are token-expensive). A server that isn't connected is a null result to report, not an error.
Output
Separate what you know from what you're guessing:
- What we found — direct evidence, each claim cited to its source.
- What we can reasonably infer — clearly labeled as inference, not fact.
- Competing hypotheses — when the evidence is ambiguous, list them; don't collapse to one.
- Sources consulted — which sources were available, which were queried, and which returned nothing. A null result is first-class evidence.
Don't fabricate a rationale to fill a gap. "No evidence found; here is the most likely explanation, low confidence" is a valid and honest answer.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 79 tokens per session scan A 9436534c7932
trove-why is a skill published in the GitHub repository bravew/trove (10 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 592 once invoked, about $0.0003 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…