Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Automatically benchmark your custom memory implementation against established systems like Supermemory.
Install Benchmark Context
$ npx skills add Signet-AI/signetai --skill benchmark-context -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Signet-AI/signetai benchmark-context --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Signet-AI/signetai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/memorybench/skills/memorybench .claude/skills/benchmark-context && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "benchmark-context" agent skill from https://github.com/Signet-AI/signetai/tree/main/memorybench/skills/memorybench into .claude/skills/benchmark-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-context", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Signet-AI/signetai/tree/main/memorybench/skills/memorybenchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Signet-AI/signetai --skill benchmark-context -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Signet-AI/signetai benchmark-context --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Signet-AI/signetai.git skills-src && mkdir -p .agents/skills && cp -r skills-src/memorybench/skills/memorybench .agents/skills/benchmark-context && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "benchmark-context" agent skill from https://github.com/Signet-AI/signetai/tree/main/memorybench/skills/memorybench into .agents/skills/benchmark-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-context", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Signet-AI/signetai --skill benchmark-context -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Signet-AI/signetai benchmark-context --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Signet-AI/signetai.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/memorybench/skills/memorybench .cursor/skills/benchmark-context && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "benchmark-context" agent skill from https://github.com/Signet-AI/signetai/tree/main/memorybench/skills/memorybench into .cursor/skills/benchmark-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-context", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Signet-AI/signetai.git --path memorybench/skills/memorybench--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Signet-AI/signetai --skill benchmark-context -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Signet-AI/signetai benchmark-context --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Signet-AI/signetai.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/memorybench/skills/memorybench .gemini/skills/benchmark-context && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "benchmark-context" agent skill from https://github.com/Signet-AI/signetai/tree/main/memorybench/skills/memorybench into .gemini/skills/benchmark-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-context", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Signet-AI/signetai benchmark-contextInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Signet-AI/signetai --skill benchmark-context -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Signet-AI/signetai.git skills-src && mkdir -p .github/skills && cp -r skills-src/memorybench/skills/memorybench .github/skills/benchmark-context && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "benchmark-context" agent skill from https://github.com/Signet-AI/signetai/tree/main/memorybench/skills/memorybench into .github/skills/benchmark-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-context", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Signet-AI/signetai --skill benchmark-context -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Signet-AI/signetai benchmark-context --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Signet-AI/signetai.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/memorybench/skills/memorybench .opencode/skills/benchmark-context && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "benchmark-context" agent skill from https://github.com/Signet-AI/signetai/tree/main/memorybench/skills/memorybench into .opencode/skills/benchmark-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-context", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
benchmark-context- GitHub stars
- 304
- Token cost
- ~3k tokens
- SKILL.md length
- 1,292 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Automatically benchmark your custom memory implementation against established systems like Supermemory.
- Works in 12 steps: Provider Name → Memory Code Location → Benchmark Dataset → …
- Agent Workflows work in your project
- SKILL.md covers What This Skill Does, When to Use This Skill, How It Works and Initial Questions, plus 8 more sections
- Calls bun and git; reaches github.com
What it does
Benchmark Context is an agent skill from Signet-AI/signetai. Automatically benchmark your custom memory implementation against established systems like Supermemory. Set up a public benchmark, or create your own. Compare solutions against quality, latency, features and cost, easily, with a simple UI and CLI.
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. The repository describes itself as: Sync and store memories, shared identity files (AGENTS.md, CLAUDE.md), session transcripts, institutional knowledge, and secrets between all of your favorite harnesses and models.
When your agent uses it
- Agent Workflows work in your project
Example prompts
- “/benchmark-context”
Workflow steps
12 steps, taken from the step headings in SKILL.md.
- Provider Name
- Memory Code Location
- Benchmark Dataset
- Comparison Targets (Multi-select)
- Test Size
- Verify Environment
- Use a pinned MemoryBench checkout
- Gather User Input
- Analyze User's Memory Code
- Generate Provider Code
- Register Provider
- Configure Environment
What it can do on your machine
Read from SKILL.md and the folder at commit aa4c499. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
bungit
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Benchmark Context loads about 3k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 1,292 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:58
- Creates `.env.local` with required API keys - NoteMentions a .env fileSKILL.md:142
├── .env.local # Your API keys - NoteMentions a .env fileSKILL.md:179
not initialized"** - Check API keys in `.env.local` - NoteMentions a .env fileSKILL.md:259
Create or update `memorybench/.env.local` with provided values.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,292 words (~3,047 tokens).
“Automatically benchmark your custom memory implementation against established systems like Supermemory, Mem0, and Zep.”
- name
- benchmark-context
Files
Just SKILL.md in memorybench/skills/memorybench of Signet-AI/signetai.
Open the folder on GitHubat commit aa4c499
Compare with similar skills
Benchmark Context next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Benchmark Context this skillSignet-AI/signetai | 304 | — | ~3k | Automated safety check: Notes | Custom licence | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Copilot Session Failure Analysisdotnet/maui | 23k | — | ~3.4k | Automated safety check: Pass | MIT | |
| Mem0 CLI Memory Commandsmem0ai/mem0 | 67k | — | ~2k | Automated safety check: Notes | Apache-2.0 | |
| Create Agentvectorize-io/hindsight | 47k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Google Antigravity SDKgoogle-antigravity/antigravity-sdk-python | 3.7k | — | ~2.1k | Automated safety check: Notes | Apache-2.0 |
Similar skills
- Official
- Official
Copilot Session Failure Analysis
dotnet/maui
Mines local Copilot CLI session logs for dotnet/maui to rank costly or failing runs, tag recurring failure modes, propose repo edits and emit guard evals.
Mem0 CLI Memory Commands
mem0ai/mem0
Adds, searches, lists, updates and deletes memories on the Mem0 platform from the terminal with the mem0 command, including a JSON mode built for agents.
Create Agent
vectorize-io/hindsight
Create a new Hindsight-powered subagent with long-term memory.
Google Antigravity SDK
google-antigravity/antigravity-sdk-python
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK.
Yao Meta Skill
yaojingang/yao-meta-skill
Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.
More from Signet-AI/signetai
All 9 skills in this repoDreaming Development
Signet-AI/signetai
A skill your agent uses for Signet Dreaming development: inspect existing source, semantic-memory, retrieval, and inference architecture before changing it; prevent duplicate modules and ad-hoc…
Benchmarking
Signet-AI/signetai
Benchmark Signet memory with MemoryBench: regression-check Dreaming and recall changes, compare models, diagnose score drops, and record results; NOT for the prompt-submit latency benchmark.
Onboarding
Signet-AI/signetai
Interactive interview to set up your Signet workspace (~5-10 minutes).
Agents Md Sync
Signet-AI/signetai
Prune and route AGENTS.md trees for durable, high-signal context.
Dreaming
Signet-AI/signetai
Maintain Signet's living ontology and memory substrate from transcripts, memory artifacts, source artifacts, notes, summaries, and imported records.
Provider SDK Upgrades
Signet-AI/signetai
Upgrade provider SDKs and refresh bundled model presets; NOT for unrelated provider architecture.
Related
Categories
Questions about Benchmark Context
What does Benchmark Context do?
Automatically benchmark your custom memory implementation against established systems like Supermemory. Benchmark Context is an agent skill from Signet-AI/signetai. Automatically benchmark your custom memory implementation against established systems like Supermemory.
When should I use Benchmark Context?
Benchmark Context fits situations like: agent Workflows work in your project.
How do I install Benchmark Context in Claude Code?
Run `npx skills add Signet-AI/signetai --skill benchmark-context -a claude-code`. Or copy the skill folder (memorybench/skills/memorybench in Signet-AI/signetai) into .claude/skills/benchmark-context in your project. Claude Code loads it when a task matches its description.
How do I install Benchmark Context in Codex?
Run `npx skills add Signet-AI/signetai --skill benchmark-context -a codex`. Or copy the skill folder (memorybench/skills/memorybench in Signet-AI/signetai) into .agents/skills/benchmark-context in your project. Codex loads it when a task matches its description.
Can I use Benchmark Context in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Signet-AI/signetai --skill benchmark-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/benchmark-context, .gemini/skills/benchmark-context, .github/skills/benchmark-context and .opencode/skills/benchmark-context in your project.
What does Benchmark Context need to run?
Going by SKILL.md and its folder, Benchmark Context needs the command-line tools its instructions call (bun and git).
Does Benchmark Context access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Benchmark Context safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Benchmark Context use?
Benchmark Context has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Benchmark Context use?
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Benchmark Context?
Skills that share tags, products or a category with Benchmark Context: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Copilot Session Failure Analysis (dotnet/maui, 23k stars), Mem0 CLI Memory Commands (mem0ai/mem0, 67k stars) and Create Agent (vectorize-io/hindsight, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Benchmark Context?
Signet-AI (a GitHub organization) maintains it in Signet-AI/signetai, which has 304 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 8, 2026.
Source: Signet-AI/signetai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.