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 k-rister/ephemeral-buffer-mcp --skill eb-activity-summarygit clone --depth 1 https://github.com/k-rister/ephemeral-buffer-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/k-rister/ephemeral-buffer-mcp/eb-activity-summary)<a href="https://agentmods.dev/skills/k-rister/ephemeral-buffer-mcp/eb-activity-summary"><img src="https://agentmods.dev/badge/skills/k-rister/ephemeral-buffer-mcp/eb-activity-summary/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/k-rister/ephemeral-buffer-mcp/eb-activity-summary"><img src="https://agentmods.dev/badge/skills/k-rister/ephemeral-buffer-mcp/eb-activity-summary.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 | $0.00048 | $0.01262 |
| Opus 5.5 | $0.00019 | $0.00505 |
| Sonnet 5.5 | $0.00010 | $0.00252 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
eb-activity-summary 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 7d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ephemeral Buffer activity summary
Produce a read-only activity report for the repository in the current
workspace. The reconstructed skill is intentionally repository-specific:
k-rister/ephemeral-buffer-mcp (project name: Ephemeral Buffer MCP, or EB).
Scope defaults
When the request does not specify them, use:
- audience: developer, including implementation, tests, documentation, CI, and release work;
- authors: all contributors to the EB repository;
- period: the previous seven days ending now, expressed with explicit local dates and UTC timestamps.
If the host supports interactive questions and the user has not already provided the scope, ask for:
- Audience: User-facing changes or Developer/all changes.
- Authors: All authors, the authenticated user, or a named GitHub user.
- Date range: Past week, past two weeks, past month, or a custom
YYYY-MM-DD..YYYY-MM-DDrange.
Do not ask again when the user has already supplied an unambiguous scope. The phrase “all EB activity” means developer/all authors unless the user says otherwise.
Collect the activity
First verify the repository identity from git remote -v or the GitHub API.
Do not silently summarize a different repository. Use read-only Git and
GitHub operations:
- commits in the interval, from the local history and, when available, the repository commits API;
- pull requests created, merged, closed, or updated in the interval, plus currently open pull requests;
- issues created, closed, or updated in the interval, plus currently open issues;
- releases published in the interval;
- GitHub Actions runs in the interval, grouped by workflow and conclusion;
- the current branch/worktree state when the report is generated.
For GitHub searches, use YYYY-MM-DD dates. For commits and workflow APIs,
use ISO 8601 timestamps with an explicit UTC offset. Prefer bounded JSON
queries and --jq projections over unbounded pages. When output could be
large, route it through the repository's ephemeral-buffer capture/search
tools and retrieve only the relevant slices.
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.
- 7d ago First seen · 124 lines · 48 tokens per session scan A aa592afe7d3b
eb-activity-summary is a skill published in the GitHub repository k-rister/ephemeral-buffer-mcp (3 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 1,262 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
cocosearch-commit
Use when committing changes — analyzes staged (or unstaged) diffs with CocoSearch semantic search and dependency impact to generate comprehensive Conventional Commit messages. Reviews changes thoroughly, then asks user to approve, edit, or abort the commit.
brpr
(devtools plugin) Create a branch, commit changes, push, and open a PR — or just commit+push+PR if already on a feature branch. Links related issues from GitHub or Linear based on project tracker config.
roadmap-task-deliver
Deliver the first eligible unfinished roadmap task through implementation, review, green CI, PR merge, and a task-status update. Use for autonomous delivery from local roadmap and task files. Files can be outside the code repository or outside Git.
phase-commit
Create one local commit for a completed, validated, and reviewed unit of work. Use only when the user explicitly requests a commit without pushing or other delivery actions.
committing
Use when creating a git commit — atomic commits, message format, what never to commit, and the agent workflow-completion requirement (run completion gate; stage or publish per publish authority).
code-review-ui
Use when reviewing frontend, UI, or component code. Covers accessibility (WCAG AA), state management, bundle size, keyboard navigation, hydration, and rendering performance. Load instead of the general code-review skill for UI-focused reviews.