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 shabaraba/vibing.nvim --skill vibing-chat-searchgit clone --depth 1 https://github.com/shabaraba/vibing.nvimWrote 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/shabaraba/vibing.nvim/vibing-chat-search)<a href="https://agentmods.dev/skills/shabaraba/vibing.nvim/vibing-chat-search"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-chat-search/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/shabaraba/vibing.nvim/vibing-chat-search"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-chat-search.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 | $0.00116 | $0.00871 |
| Opus 5 | $0.00058 | $0.00436 |
| Sonnet 5 | $0.00023 | $0.00174 |
| Haiku 4.5 | $0.00012 | $0.00087 |
Grade A, and why
vibing-chat-search 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibing-chat-search
Finds past vibing.nvim chat files relevant to a natural-language query, by grepping
.vibing/chat/ for keyword candidates and then reading the survivors to judge actual relevance.
When this applies
- The user asks something like "前に〜について聞いたことあったっけ" / "did we discuss X before" / "find the chat where I asked about Y".
- Claude suspects a similar topic was covered in an earlier, different conversation.
- Invoked directly via
/vibing-chat-search.
Not for re-reading this conversation's own history after context loss — that's
vibing-chat-recall.
Step 1: Locate the chat directory
Resolve .vibing/chat/ relative to the git repository root:
git rev-parse --show-toplevel
Then check <root>/.vibing/chat/ exists. If the repo has no .vibing/chat/ directory (not a
git repo, or the directory is missing), fall back to .vibing/chat/ relative to the current
working directory. If neither exists, tell the user no chat history was found and stop.
Step 2: Build search keywords
From the user's natural-language query, extract 2-4 candidate keywords or short phrases, including obvious synonyms/rephrasings — chat content is free-form Japanese or English prose, not structured data, so a single literal substring rarely covers how the topic was actually phrased.
Example: query "前にwebfetchのURL表示について話した?" → candidates: webfetch, WebFetch,
URL表示, 閲覧したurl.
Step 3: Narrow candidates with Grep
Search both User and Assistant content — don't restrict to ## User sections only, since the
user's original phrasing may be vague while the topic keyword shows up clearly in Claude's own
reply.
Use the Grep tool with path: ".vibing/chat", one call per keyword (or a regex alternation),
output_mode: "files_with_matches". Union the results across all keywords into one candidate
list.
If the candidate list is larger than ~15 files, don't read them all — narrow further:
- Re-run with
output_mode: "count"and keep only the files with the highest match counts, or - Tighten the keyword list to more specific terms before re-searching.
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.
- 10d ago First seen · 78 lines · 116 tokens per session scan A e310b6c2757a
vibing-chat-search is a skill published in the GitHub repository shabaraba/vibing.nvim (13 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 871 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
context-optimizer
Reduce Claude AI token consumption by 5x-27x using prompt-native workflows and structural code manifests. Forces Claude to reason from CONTEXTMANIFEST.md first, fetch max 3 files per turn, and output in a strict compressed format. Use when user says optimize context, reduce tokens, context optimizer, manifest, blast…
context-optimizer
Reduce Claude AI token consumption by 5x-27x using prompt-native workflows and structural code manifests. Forces Claude to reason from CONTEXTMANIFEST.md first, fetch max 3 files per turn, and output in a strict compressed format. Use when user says optimize context, reduce tokens, context optimizer, manifest, blast…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
vellum-memory-v2-migration
Perform a one-time migration from memory v1, to memory v2, which was introduced in 0.8.0.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…