Agent skill

Toolkit

Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.

Install Toolkit

skills CLI

$ npx skills add notque/vexjoy-agent --skill toolkit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install notque/vexjoy-agent toolkit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/notque/vexjoy-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/meta/toolkit .claude/skills/toolkit && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "toolkit" agent skill from https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit into .claude/skills/toolkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toolkit", 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

$skill-installer install https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit

Type 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.

skills CLI

$ npx skills add notque/vexjoy-agent --skill toolkit -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install notque/vexjoy-agent toolkit --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/notque/vexjoy-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/meta/toolkit .agents/skills/toolkit && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "toolkit" agent skill from https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit into .agents/skills/toolkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toolkit", 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.

skills CLI

$ npx skills add notque/vexjoy-agent --skill toolkit -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install notque/vexjoy-agent toolkit --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/notque/vexjoy-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/meta/toolkit .cursor/skills/toolkit && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "toolkit" agent skill from https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit into .cursor/skills/toolkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toolkit", 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

$ gemini skills install https://github.com/notque/vexjoy-agent.git --path skills/meta/toolkit

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add notque/vexjoy-agent --skill toolkit -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install notque/vexjoy-agent toolkit --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/notque/vexjoy-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/meta/toolkit .gemini/skills/toolkit && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "toolkit" agent skill from https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit into .gemini/skills/toolkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toolkit", 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.

GitHub CLI

$ gh skill install notque/vexjoy-agent toolkit

Installs 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).

skills CLI

$ npx skills add notque/vexjoy-agent --skill toolkit -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/notque/vexjoy-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/meta/toolkit .github/skills/toolkit && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "toolkit" agent skill from https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit into .github/skills/toolkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toolkit", 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.

skills CLI

$ npx skills add notque/vexjoy-agent --skill toolkit -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install notque/vexjoy-agent toolkit --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/notque/vexjoy-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/meta/toolkit .opencode/skills/toolkit && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "toolkit" agent skill from https://github.com/notque/vexjoy-agent/tree/main/skills/meta/toolkit into .opencode/skills/toolkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "toolkit", 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: toolkit
GitHub stars: 435
Token cost: ~3.1k tokens
SKILL.md length: 1,132 words
Files: 91 (incl. scripts, references, assets)
Skills in repo: 61
Repo updated: Oct 3, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.

Works in 5 steps: Capture intent. What should the skill… → Duplicate check. Run grep -i ""… → Write SKILL.md. Follow… → …
Tasks that involve Agent instruction files
SKILL.md covers Mode Selection, Create Skill, Create Agent and Uplift for Weaker Models, plus 8 more sections
Calls python3

What it does

Toolkit is an agent skill from notque/vexjoy-agent. Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 96 other files, including scripts, reference files and assets (for example `agents/skill-creator/analyzer.md`, `agents/skill-creator/comparator.md` and `agents/skill-creator/grader.md`).

It sits in Agent Workflows, covering Agent instruction files, Building AI agents and Agent evaluation and testing. The repository describes itself as: VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop. The licence is MIT.

When your agent uses it

Tasks that involve Agent instruction files
Tasks that involve Building AI agents
Tasks that involve Agent evaluation and testing

Example prompts

“/toolkit”

Requirements

Python 3
Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Glob, Grep, Agent, Task, Skill

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

Capture intent. What should the skill do? When should it trigger? What output? Are outputs objectively verifiable (code, data) or…
Duplicate check. Run grep -i "" skills/*/SKILL.md to check existing coverage. If an umbrella skill covers the domain, add a reference file…
Write SKILL.md. Follow references/skill-creator/skill-template.md for frontmatter structure. Apply Dense-Complete Writing standard…
Test. Try 3 should-trigger, 2 should-not-trigger, and 2 near-miss prompts with the skill loaded. Revise the SKILL.md until routing and…
Register. Run python3 scripts/generate-skill-index.py to update routing.

What it can do on your machine

Read from SKILL.md and the folder at commit 5218674. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Read
- Write
- Edit
- Bash
- Glob
- Grep
- Agent
- Task
- Skill
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Toolkit loads about 3.1k tokens when it runs, and up to ~112k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 1,132 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~27
When it runs · the whole SKILL.md, loaded when a task matches: ~3.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~112k

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.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Agent, Task, Skill

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); the scripts in this folder are not scanned.

SKILL.md

The full file from notque/vexjoy-agent at commit 5218674, republished under its MIT licence (© notque). 1,132 words, ~3,069 tokens.

Download SKILL.mdSave it as .claude/skills/toolkit/SKILL.md (or your agent's skills folder). This skill also uses 90 other files; get the full folder from GitHub.

name: toolkit
description: Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.
allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Agent, Task, Skill
user-invocable: true
agent: toolkit-governance-engineer
routing.force_route: true
routing.not_for: application code (use workflow), code review (use review)
routing.triggers: create skill, create agent, scaffold skill, scaffold agent, new skill, new agent, skill template, agent template, eval skill, evaluate agent, benchmark skill…
routing.category: meta-tooling
routing.pairs_with: review, workflow

Toolkit

Nine modes covering the full toolkit lifecycle: creating and improving skills and agents; evaluating agents; maintaining routing tables; generating CLAUDE.md; composing multi-skill DAGs; and running the evolution loop. Classify the request and follow the matching section.

Mode Selection

Mode	Signals	Section
Skill Creator	create skill, scaffold skill, new skill, build a skill	Create Skill
Agent Creator	create agent, scaffold agent, new agent	Create Agent
Weak-Model Uplift	weaker model, uplift skill, make a skill work for Opus 4.6, improve guidance from generated output	Uplift for Weaker Models
Agent Comparison	compare agents, A/B test agents, benchmark agents, benchmark skill, bake-off	Compare Agents
Agent Evaluation	evaluate agent quality, audit agent, grade agent, eval skill	Evaluate Agent
Skill Composer	compose skills, DAG orchestration, skill pipeline	Compose Skills
Routing Tables	update routing tables, sync routing, routing drift	Update Routing
Toolkit Evolution	evolve toolkit, self-improve, discover gaps	Evolve Toolkit
Generate CLAUDE.md	generate claude.md, create claude.md, init	Generate CLAUDE.md

Create Skill

Phases: INTENT -> DRAFT -> TEST -> REGISTER

Capture intent. What should the skill do? When should it trigger? What output? Are outputs objectively verifiable (code, data) or subjective (writing, design)?
Duplicate check. Run grep -i "<domain>" skills/*/SKILL.md to check existing coverage. If an umbrella skill covers the domain, add a reference file instead.
Write SKILL.md. Follow references/skill-creator/skill-template.md for frontmatter structure. Apply Dense-Complete Writing standard. Frontmatter must include: name, description, routing (triggers, not_for, category, pairs_with), allowed-tools.
Test. Try 3 should-trigger, 2 should-not-trigger, and 2 near-miss prompts with the skill loaded. Revise the SKILL.md until routing and output are right.
Register. Run python3 scripts/generate-skill-index.py to update routing.

Load references/skill-creator.md for the full workflow. Deep references in references/skill-creator/ cover progressive disclosure, artifact schemas, complexity tiers, error catalog, enrichment workflow, and more.

Scripts: scripts/skill-creator/

Create Agent

Phases: DISCOVER -> DESIGN -> SCAFFOLD -> REGISTER -> VALIDATE

Discover. Check for domain overlap: grep -i "<domain>" agents/*.md. If an existing agent covers the domain, add a references/ file instead.
Design. Decide role type (reviewer/engineer/orchestrator), allowed tools, complexity, triggers (3-6 specific phrases), pairs_with (verify each exists), reference files, description (intent verb + domain + boundary clause), activation cases.
Scaffold. Write the agent file using references/agent-creator/agent-frontmatter-template.md. Follow docs/PHILOSOPHY.md for operator context structure.
Register. Run python3 scripts/generate-agent-index.py.
Validate. Run python3 scripts/validate-references.py to check reference file integrity. Test activation with the 3+2+2 prompt set.

Load references/agent-creator.md for full phases. Deep references in references/agent-creator/ cover design patterns, frontmatter template, eval design.

Uplift for Weaker Models

Improve a skill, agent, or shared guide until a weaker model produces strong output with it. Load references/weak-model-uplift.md and follow its steps:

Pick the target from data. Query ~/.claude/learning/usage.db and learning.db for heavily used or failing skills.
Build tasks and checks first. 4–8 tasks plus 1–2 held-out tasks; deterministic checks and a yes/no rubric written before any run.
Run the arms. No guidance and current guidance, two samples per task minimum, with python3 scripts/weak_model_run.py.
Score and look. Checks, rubric, your own review of every artifact, optional Jev questions on extracted facts.
Turn failures into rules. Concrete values, before/after examples, runnable checks; delete stale instructions; examples from unrelated products.
Rerun the guided arm and held-out tasks; stop when gains flatten or after three rounds.
Report and ship a per-round table with held-out results, cost, and caveats in the PR body.

Compare Agents

Controlled benchmarks comparing agent variants on identical tasks.

Select variants. Identify the agents to compare (2-4 variants).
Design benchmark. Load references/agent-comparison/benchmark-tasks.md. Select 5-10 representative tasks covering the agent's domain.
Execute. Run each task with each variant. Collect: output quality, token usage, tool calls, time.
Grade. Apply rubric from references/agent-comparison/grading-rubric.md. Score each dimension.
Report. Use references/agent-comparison/report-template.md. Include: methodology, per-task scores, aggregate rankings, cost analysis, recommendation.
Optimize. Load references/agent-comparison/optimize-phase.md to improve the winning variant further.

Load references/agent-comparison.md for the full methodology.

Evaluate Agent

Static structural and standards-compliance grading with a 90-point deterministic scorer.

Read the agent file. Extract frontmatter, body sections, reference files.
Score. Apply rubric from references/agent-evaluation/scoring-rubric.md. Categories: identity (15 pts), expertise (20 pts), routing (15 pts), references (15 pts), workflow (15 pts), standards (10 pts).
Report. Use references/agent-evaluation/report-templates.md. Include: per-category scores, specific findings, improvement recommendations.
Batch mode. For multiple agents: references/agent-evaluation/batch-evaluation.md.

Load references/agent-evaluation.md for the full methodology.

Show full SKILL.md (426 more words)Show less

Compose Skills

DAG-based multi-skill orchestration with dependency resolution.

Define the DAG. List skills in execution order. Identify dependencies (skill B needs output from skill A).
Check compatibility. Load references/skill-composer/compatibility-matrix.md. Verify input/output contracts between skills.
Build the pipeline. Load references/skill-composer/composition-patterns.md for orchestration patterns (serial, parallel, fan-out, conditional).
Execute. Run skills in DAG order. Pass outputs between skills via the defined contracts.
Validate. Check all skills completed. Verify final output meets the composite goal.

Load references/skill-composer.md for the full methodology. See references/skill-composer/examples.md for worked examples.

Scripts: scripts/skill-composer/

Update Routing

5-phase pipeline: SCAN -> EXTRACT -> GENERATE -> UPDATE -> VERIFY.

SCAN. Run python3 scripts/generate-skill-index.py to discover all skills and agents.
EXTRACT. Parse frontmatter from each SKILL.md and agent file. Extract triggers, description, category, complexity.
GENERATE. Build skills/INDEX.json and agents/INDEX.json.
UPDATE. Write index files. PostToolUse hooks auto-regenerate on individual edits; this covers bulk changes and drift.
VERIFY. Compare generated index against discovered files. Report missing entries, conflicts, or stale entries.

Load references/routing-table-updater.md for full phases. Deep references in references/routing-table-updater/ cover routing format, extraction patterns, conflict resolution, batch mode.

Evolve Toolkit

7-phase pipeline: DISCOVER -> DIAGNOSE -> PROPOSE -> CRITIQUE -> BUILD -> VALIDATE -> EVOLVE.

DISCOVER. Audit recent sessions for routing failures, skill gaps, agent weaknesses, user friction.
DIAGNOSE. Load references/toolkit-evolution/diagnose-scripts.md. Run gap analysis scripts. Identify patterns.
PROPOSE. Generate 3-5 improvement proposals with expected impact, effort, risk.
CRITIQUE. Apply multi-perspective review to proposals.
BUILD. Implement the approved proposals using the appropriate mode above (create skill, create agent, etc.).
VALIDATE. Run tests and validators on new/changed components.
EVOLVE. Update evolution history at references/toolkit-evolution/evolution-history.md.

Load references/toolkit-evolution.md for the full pipeline.

Generate CLAUDE.md

4-phase pipeline: SCAN -> DETECT -> GENERATE -> VALIDATE.

SCAN. Check for existing CLAUDE.md. If present, write to CLAUDE.md.generated for comparison. Detect language, framework, build system from repo files.
DETECT. Identify domain enrichment opportunities. Load references/generate-claudemd/examples-and-errors.md for language-specific patterns.
GENERATE. Load template from references/generate-claudemd/CLAUDEMD_TEMPLATE.md. Fill sections: overview, commands, architecture, conventions, testing, deployment.
VALIDATE. Run all documented commands. Verify paths exist. Check for secrets in output.

Optional modes: subdirectory CLAUDE.md for monorepos; minimal mode (overview + commands + architecture only).

Deep References

Load when the task needs detailed schemas, templates, or methodology.

Mode	Key References
Skill Creator	`references/skill-creator.md`, `references/skill-creator/{skill-template,progressive-disclosure,complexity-tiers,error-catalog,enrichment-workflow}.md`
Agent Creator	`references/agent-creator.md`, `references/agent-creator/{agent-design-patterns,agent-frontmatter-template,agent-eval-design}.md`
Weak-Model Uplift	`references/weak-model-uplift.md`
Agent Comparison	`references/agent-comparison.md`, `references/agent-comparison/{methodology,grading-rubric,benchmark-tasks,report-template,optimize-phase}.md`
Agent Evaluation	`references/agent-evaluation.md`, `references/agent-evaluation/{scoring-rubric,report-templates,batch-evaluation}.md`
Skill Composer	`references/skill-composer.md`, `references/skill-composer/{compatibility-matrix,composition-patterns,skill-patterns,examples}.md`
Routing Tables	`references/routing-table-updater.md`, `references/routing-table-updater/{routing-format,extraction-patterns,conflict-resolution,examples}.md`
Toolkit Evolution	`references/toolkit-evolution.md`, `references/toolkit-evolution/{diagnose-scripts,evolution-history,evolve-preferred-patterns}.md`
Generate CLAUDE.md	`references/generate-claudemd.md`, `references/generate-claudemd/{CLAUDEMD_TEMPLATE,examples-and-errors}.md`

Scripts and Agents

Mode	Scripts	Agents
Skill Creator	`scripts/skill-creator/`	`agents/skill-creator/`
Skill Composer	`scripts/skill-composer/`	--
Weak-Model Uplift	`scripts/weak_model_run.py` (repo root)	--
Routing Tables	`scripts/routing-table-updater/`	--
Agent Comparison	`scripts/agent-comparison/`	--

Files

SKILL.md and 90 other files (scripts, references, assets) in skills/meta/toolkit of notque/vexjoy-agent.

SKILL.md
agents/skill-creator/analyzer.md
agents/skill-creator/comparator.md
agents/skill-creator/grader.md
assets/skill-creator/eval_viewer.html
references/agent-comparison.md
references/agent-comparison/benchmark-tasks.md
references/agent-comparison/do-creation-compliance-tasks.json
references/agent-comparison/examples-and-errors.md
references/agent-comparison/grading-rubric.md
references/agent-comparison/methodology.md
references/agent-comparison/optimization-guide.md
references/agent-comparison/optimization-tasks.example.json
references/agent-comparison/optimize-phase.md
references/agent-comparison/read-only-ops-short-tasks.json
… and 76 more

Open the folder on GitHubat commit 5218674

Compare with similar skills

Toolkit 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.

Toolkit compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Toolkit this skillnotque/vexjoy-agent	435	—	~3.1k	Automated safety check: Notes	MIT	4 days ago
Microsoft Foundrymicrosoft/GitHub-Copilot-for-Azure	255	1 repos	~6.7k	Automated safety check: Pass	MIT	today
Agent Self-Customizationnanocoai/nanoclaw	31k	1 repos	~1.5k	Automated safety check: Notes	MIT	yesterday
Harness Evaltech-leads-club/agent-skills	7k	—	~3.9k	Automated safety check: Pass	CC-BY-4.0	17 days ago
Agentic Harness Design and ReviewNateBJones-Projects/OB1	4.7k	—	~1.8k	Automated safety check: Pass	Custom licence	yesterday
Learn From History AuditKonghaYao/peri	223	—	~3.5k	Automated safety check: Pass	Apache-2.0	today

Similar skills

Microsoft Foundry
microsoft/GitHub-Copilot-for-Azure
Official
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end.
255 GitHub starsUsed in 1 repo~6.7k tokens
AI & LLM EngineeringAuto-check passed
Agent Self-Customization
nanocoai/nanoclaw
A decision tree for an agent changing its own setup: edit memory directly, request approval for packages and MCP servers, and delegate code edits to a builder agent.
31k GitHub starsUsed in 1 repo~1.5k tokens
Agent WorkflowsAuto-check: notes
Harness Eval
tech-leads-club/agent-skills
Evaluates a repository's agent harness (AGENTS.md, rules, skills) for broken paths, redundant instructions and usefulness, and stops at reports.
7k GitHub stars~3.9k tokensUpdated 17 days ago
Agent WorkflowsAuto-check passed
Agentic Harness Design and Review
NateBJones-Projects/OB1
Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.
4.7k GitHub stars~1.8k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Learn From History Audit
KonghaYao/peri
Audits recent agent conversation history and turns repeated failures and successes into testable harness improvement proposals that later audits can check.
223 GitHub stars~3.5k tokensUpdated today
Agent WorkflowsAuto-check passed
Agents Md Generator
julianromli/opencode-template
Generate hierarchical AGENTS.md structures for codebases. An agent skill from julianromli/opencode-template.
144 GitHub starsUsed in 1 repo~1.4k tokens
Agent WorkflowsAuto-check: notes

Questions about Toolkit

What does Toolkit do?

Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md. Toolkit is an agent skill from notque/vexjoy-agent.md.

When should I use Toolkit?

Toolkit fits situations like: tasks that involve Agent instruction files; tasks that involve Building AI agents; tasks that involve Agent evaluation and testing.

How do I install Toolkit in Claude Code?

Run `npx skills add notque/vexjoy-agent --skill toolkit -a claude-code`. Or copy the skill folder (skills/meta/toolkit in notque/vexjoy-agent) into .claude/skills/toolkit in your project. Claude Code loads it when a task matches its description.

How do I install Toolkit in Codex?

Run `npx skills add notque/vexjoy-agent --skill toolkit -a codex`. Or copy the skill folder (skills/meta/toolkit in notque/vexjoy-agent) into .agents/skills/toolkit in your project. Codex loads it when a task matches its description.

Can I use Toolkit 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 notque/vexjoy-agent --skill toolkit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/toolkit, .gemini/skills/toolkit, .github/skills/toolkit and .opencode/skills/toolkit in your project.

What does Toolkit need to run?

Going by SKILL.md and its folder, Toolkit needs the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Glob, Grep, Agent, Task, Skill.

Does Toolkit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Toolkit safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Toolkit use?

Toolkit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Toolkit use?

About 3.1k 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. Its references folder adds about 109k tokens, read only when the agent opens those files.

What are the alternatives to Toolkit?

Skills that share tags, products or a category with Toolkit: Microsoft Foundry (microsoft/GitHub-Copilot-for-Azure, 255 stars), Agent Self-Customization (nanocoai/nanoclaw, 31k stars), Harness Eval (tech-leads-club/agent-skills, 7k stars) and Agentic Harness Design and Review (NateBJones-Projects/OB1, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Toolkit?

notque (a GitHub user) maintains it in notque/vexjoy-agent, which has 435 GitHub stars. The repository holds 61 skills in this directory. The repository was last updated on October 3, 2026.

Source: notque/vexjoy-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Toolkit

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Toolkit

Mode Selection

Create Skill

Create Agent

Uplift for Weaker Models

Compare Agents

Evaluate Agent

Compose Skills

Update Routing

Evolve Toolkit

Generate CLAUDE.md

Deep References

Scripts and Agents

Files

Compare with similar skills

Similar skills

More from notque/vexjoy-agent

Related

Questions about Toolkit