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-recallgit 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-recall)<a href="https://agentmods.dev/skills/shabaraba/vibing.nvim/vibing-chat-recall"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-chat-recall/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-recall"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-chat-recall.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 | $0.00130 | $0.00818 |
| Opus 5 | $0.00065 | $0.00409 |
| Sonnet 5 | $0.00026 | $0.00164 |
| Haiku 4.5 | $0.00013 | $0.00082 |
Grade A, and why
vibing-chat-recall 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 2d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibing-chat-recall
Restores this conversation's own context after it appears to have been lost (session reset, dropped RPC connection, compaction) by re-reading the live vibing.nvim chat buffer this conversation is running in.
When this applies
- The user explicitly asks to "思い出して" / "recall" / "re-read the chat history".
- Claude notices its own responses no longer track what was discussed earlier in this same conversation — a sign the session was silently reset or compacted.
- Invoked directly via
/vibing-chat-recall.
This skill only makes sense inside a vibing.nvim chat session. If the environment doesn't look like one (see below), say so briefly and stop — don't guess at a file to read.
Locating this conversation's own chat buffer
Every request sent through vibing.nvim's Claude CLI adapter carries one extra line appended to the system prompt:
Current vibing.nvim chat buffer number: 12
Use that buffer number — never rely on which Neovim window currently has focus, since the user
may have switched away, or another chat may be running concurrently. It is a buffer number rather
than a path so that :VibingSetFileTitle renaming the chat mid-conversation neither breaks this
lookup nor invalidates the prompt cache.
If that line isn't present in the system prompt, this skill isn't running inside vibing.nvim (or is running against an older vibing.nvim build that doesn't send it yet). Tell the user briefly and stop.
Reading the buffer
The MCP server is already bound to this chat's Neovim, so omit rpc_port on both calls below. If the
mcp__vibing-nvim__ prefix is unavailable, look for a tool name ending in the one you need —
loaded as a plugin they are mcp__plugin_vibing-nvim_vibing-nvim__<tool>. The
nvim-context skill explains both in full.
- Call
mcp__vibing-nvim__nvim_get_bufferwith thebufnrfrom the system prompt to fetch the buffer's current content. This is the live in-memory content, including edits that haven't been written to disk yet — vibing.nvim chat buffers are not auto-saved, so the on-disk file can lag behind what's actually been discussed. - If that call reports an invalid buffer — a resumed conversation can replay a buffer number
from an earlier Neovim session — call
mcp__vibing-nvim__nvim_list_buffers, find the chat file by name, and use its currentbufnr. - If the RPC connection itself is down (Neovim not reachable), there is no fallback: every other route to the buffer goes over the same channel. Tell the user briefly and stop.
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.
- 2d ago Changed · -2 lines 82e9c18499eb
- 10d ago First seen · 64 lines · 130 tokens per session scan A be9018a74a07
vibing-chat-recall is a skill published in the GitHub repository shabaraba/vibing.nvim (13 stars, last pushed yesterday), licensed MIT. It adds 130 tokens to every session and 818 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…