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 bnomei/tmux-mcp --skill tmux-buffer-explorergit clone --depth 1 https://github.com/bnomei/tmux-mcpWrote 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/bnomei/tmux-mcp/tmux-buffer-explorer)<a href="https://agentmods.dev/skills/bnomei/tmux-mcp/tmux-buffer-explorer"><img src="https://agentmods.dev/badge/skills/bnomei/tmux-mcp/tmux-buffer-explorer/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/bnomei/tmux-mcp/tmux-buffer-explorer"><img src="https://agentmods.dev/badge/skills/bnomei/tmux-mcp/tmux-buffer-explorer.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 | $0.00033 | $0.01040 |
| Opus 5 | $0.00016 | $0.00520 |
| Sonnet 5 | $0.00007 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
tmux-buffer-explorer 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 9d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tmux Buffer Explorer
When to use
- Buffer-backed data is large and cannot be loaded in one response.
- The task needs incremental search, slicing, and synthesis.
- Deterministic offsets and pagination are important.
Tools
- list-buffers
- show-buffer
- search-buffer
- subsearch-buffer
- set-buffer
- load-buffer
- append-buffer
- rename-buffer (optional)
- delete-buffer (optional)
Workflow
- List and prioritize
- Call list-buffers and prefer likely sources by size_bytes/order_index.
- Import local files when needed
- If the source is a local file, use load-buffer(name, path) instead of pasting content into set-buffer.
- Search first
- Use search-buffer with a focused query and mode (literal/regex).
- search-buffer requires UTF-8 buffers and returns byte-based offsets.
- Optional: includeSimilarity=true and/or similarityThreshold for fuzzy scoring.
- If truncated_buffers or resume_from_offset is returned, re-invoke search-buffer with resumeFromOffset (per-buffer byte offsets).
- Prefer buffers=[...] but buffer="name" is accepted as a shorthand.
- Inspect bounded slices
- Use show-buffer with offset_bytes/max_bytes around matches.
- show-buffer returns plain text and may replace invalid UTF-8 bytes.
- Use subsearch-buffer anchored to a match for localized refinement (requires UTF-8 content and may error if invalid). subsearch-buffer also accepts resumeFromOffset within the anchor window.
- subsearch-buffer expects buffer (top-level) and anchor={offsetBytes, matchLen}. It will also accept anchor.buffer if top-level buffer is omitted. matchId is not a valid anchor.
- Summarize and persist
- Store notes in set-buffer or append-buffer.
- If a non-UTF8 error appears during search/subsearch, pick a different buffer or narrow scope.
- Iterate
- Refine queries based on prior results.
- Avoid full-buffer reads unless the buffer is known small.
Decision rules
- If the user asks "near/around/within N of X", first search-buffer for X, then subsearch-buffer for the target term anchored on the chosen match.
- Avoid regex proximity across large buffers; prefer subsearch for deterministic, bounded windows.
- When multiple matches are returned, ask the user to pick a match unless the first match is obviously sufficient.
- Default window sizes: context_bytes=200; bump to 400–800 if no hits.
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.
- 9d ago First seen · 148 lines · 33 tokens per session scan A 6a5807252e2a
tmux-buffer-explorer is a skill published in the GitHub repository bnomei/tmux-mcp (52 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,040 once invoked, about $0.0002 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
ccal
Chinese Calendar with Lunar-Solar Conversion.
x-theme
Change terminal command line prompt theme. Globally manage the display style of all x-cmd interactive components. Supports multiple theme vendors: theme, starship, ohmyposh. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
loop
Schedule recurring tasks with notifications. Triggered by "/loop " to set up periodic monitoring.
log-work
Log the work segment that you did after the last work log until now in a.
skill0
Root index of x-cmd skill0 sub-skills. Defines the OKR-style agent workflow (goal → rule-verified results → execute), skill discovery, and agent tooling preferences. Style: principle-first, concise, delegate specifics to authoritative external sources.
x-starship
Starship.rs cross-shell prompt with theme management. Minimal, blazing-fast, and infinitely customizable prompt. Auto-downloads starship binary if not available. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.