Pydantic AI Harness
pydantic/pydantic-ai
Adds optional capabilities to Pydantic AI agents from pydantic-ai-harness, led by Code Mode, which runs many tool calls as one sandboxed Python script.
WORKFLOW SKILL — Creates, restructures, and audits GitHub Copilot .agent.md and .prompt.md files with correct frontmatter, handoffs, model policy, context budgets, and validation.
Install Apex Agent Authoring
$ npx skills add jonathan-vella/apex --skill apex-agent-authoring -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jonathan-vella/apex apex-agent-authoring --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/jonathan-vella/apex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/apex-agent-authoring .claude/skills/apex-agent-authoring && 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 "apex-agent-authoring" agent skill from https://github.com/jonathan-vella/apex/tree/main/.github/skills/apex-agent-authoring into .claude/skills/apex-agent-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apex-agent-authoring", 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/jonathan-vella/apex/tree/main/.github/skills/apex-agent-authoringType 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 jonathan-vella/apex --skill apex-agent-authoring -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jonathan-vella/apex apex-agent-authoring --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jonathan-vella/apex.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/apex-agent-authoring .agents/skills/apex-agent-authoring && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "apex-agent-authoring" agent skill from https://github.com/jonathan-vella/apex/tree/main/.github/skills/apex-agent-authoring into .agents/skills/apex-agent-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apex-agent-authoring", 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 jonathan-vella/apex --skill apex-agent-authoring -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jonathan-vella/apex apex-agent-authoring --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jonathan-vella/apex.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/apex-agent-authoring .cursor/skills/apex-agent-authoring && 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 "apex-agent-authoring" agent skill from https://github.com/jonathan-vella/apex/tree/main/.github/skills/apex-agent-authoring into .cursor/skills/apex-agent-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apex-agent-authoring", 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/jonathan-vella/apex.git --path .github/skills/apex-agent-authoring--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 jonathan-vella/apex --skill apex-agent-authoring -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jonathan-vella/apex apex-agent-authoring --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jonathan-vella/apex.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/apex-agent-authoring .gemini/skills/apex-agent-authoring && 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 "apex-agent-authoring" agent skill from https://github.com/jonathan-vella/apex/tree/main/.github/skills/apex-agent-authoring into .gemini/skills/apex-agent-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apex-agent-authoring", 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 jonathan-vella/apex apex-agent-authoringInstalls 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 jonathan-vella/apex --skill apex-agent-authoring -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jonathan-vella/apex.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/apex-agent-authoring .github/skills/apex-agent-authoring && 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 "apex-agent-authoring" agent skill from https://github.com/jonathan-vella/apex/tree/main/.github/skills/apex-agent-authoring into .github/skills/apex-agent-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apex-agent-authoring", 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 jonathan-vella/apex --skill apex-agent-authoring -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jonathan-vella/apex apex-agent-authoring --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jonathan-vella/apex.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/apex-agent-authoring .opencode/skills/apex-agent-authoring && 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 "apex-agent-authoring" agent skill from https://github.com/jonathan-vella/apex/tree/main/.github/skills/apex-agent-authoring into .opencode/skills/apex-agent-authoring/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apex-agent-authoring", 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
apex-agent-authoring- GitHub stars
- 217
- Token cost
- ~1.8k tokens
- SKILL.md length
- 669 words
- Files
- 10 (incl. references)
- Skills in repo
- 39
- Repo updated
- First seen
- Licence
- MIT
At a glance
WORKFLOW SKILL — Creates, restructures, and audits GitHub Copilot .agent.md and .prompt.md files with correct frontmatter, handoffs, model policy, context budgets, and validation.
- Works in 5 steps: Classify The Change → Establish Ownership → Budget Context → …
- : routine edits covered by auto-loaded instructions
- SKILL.md covers When To Use This Skill, Prerequisites, Workflow and Output Expectations, plus 2 more sections
- Calls npm and node
What it does
Apex Agent Authoring is an agent skill from jonathan-vella/apex. WORKFLOW SKILL — Creates, restructures, and audits GitHub Copilot .agent.md and .prompt.md files with correct frontmatter, handoffs, model policy, context budgets, and validation. WHEN: "create agent", "author custom agent", "edit agent definition", "agent architecture", "reduce agent tokens", "agent prompt audit". DO NOT USE FOR: routine edits covered by auto-loaded instructions.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `references/agent-file-structure.md`, `references/assess-agents.md` and `references/assess-github-folder.md`).
It sits in AI & LLM Engineering, covering Building AI agents and Context engineering. The repository describes itself as: APEX turns Azure platform engineering requirements into verified, deploy-ready IaC — powered by GitHub Copilot agents, real-time pricing, and built-in compliance. The licence is MIT.
When your agent uses it
- : routine edits covered by auto-loaded instructions
- Tasks that involve Building AI agents
- Tasks that involve Context engineering
Example prompts
- “create agent”
- “author custom agent”
- “edit agent definition”
- “/apex-agent-authoring”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit b8e5908. 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:
npmnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
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
Apex Agent Authoring loads about 1.8k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 103 tokens; SKILL.md has 669 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 passed
The automated check found no risky patterns in SKILL.md.
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
The full file from jonathan-vella/apex at commit b8e5908, republished under its MIT licence (© jonathan-vella). 669 words, ~1,750 tokens.
Download SKILL.mdSave it as
.claude/skills/apex-agent-authoring/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- apex-agent-authoring
- description
- **WORKFLOW SKILL** — Creates, restructures, and audits GitHub Copilot `.agent.md` and `.prompt.md` files with correct frontmatter, handoffs, model policy, context budgets, and validation. WHEN: "create agent", "author custom agent", "edit agent definition", "agent architecture", "reduce agent tokens", "agent prompt audit". DO NOT USE FOR: routine edits covered by auto-loaded instructions.
- user-invocable
- true
- disable-model-invocation
- false
- argument-hint
- agent or prompt path and authoring scope
- license
- MIT
- metadata.author
- jonathan-vella
- metadata.version
- 1.0
- metadata.category
- agent-development
Agent Authoring
Create and restructure Copilot agents without loading extended authoring guidance
into every ordinary agent turn. The thin enforcement layer remains in
agent-authoring.instructions.md.
When To Use This Skill
- Create a new
.agent.mdor.prompt.md. - Restructure an oversized or duplicated agent definition.
- Design handoffs or subagent boundaries.
- Select or upgrade an agent model.
- Audit fixed context cost, tool scope, or prompting structure.
- Investigate an agent validation failure requiring more than a local fix.
Do not load this skill for a routine edit where the thin instruction already states the applicable rule.
Prerequisites
- Read the target file and its nearest analogous agent once.
- Check
.github/skills/apex-workflow-engine/templates/workflow-graph.jsonbefore changing workflow topology. - Check
.github/model-catalog.jsonbefore changing model labels. - Preserve user changes and existing runtime contracts.
- Validate every model fallback; preserve exact catalog labels and unknown metadata.
- Distinguish Local prompt adapters from shared Host-compatible skills; neither static validation nor a catalog entry proves native model eligibility.
Workflow
1. Classify The Change
Choose the smallest applicable path:
| Change | Load |
|---|---|
| Frontmatter field or handoff correction | Agent file structure |
| New agent or major body restructure | Authoring workflow |
| Model assignment or effort policy | Model policy |
| Tool-heavy runtime or fallback behavior | Runtime guardrails |
| Decision capture behavior | Decision logging |
| Vendor-specific prompt audit | Ask the user to invoke /apex-vendor-prompting; do not load it automatically |
Load only the references needed for the selected path. The vendor audit skill is manual-only. Its thin instructions and required validators still apply during authoring; do not read the skill body as a workaround for its invocation flag.
2. Establish Ownership
Keep each concern in one place:
- Agent body: role, goal, workflow-specific constraints, output, stop rules.
- Sol/Terra/Luna main bodies use concise Markdown as an APEX convention, not a
model-specific vendor claim. Claude (Opus/Sonnet 5.5) main bodies use the Claude
contract: H1,
## Role,<scope_fencing>,<output_contract>,<stop_conditions>. Leaf workers use bounded role contracts instead of mandatory personality or main-agent sections. Preserve content when removing XML. - Instruction: enforceable rules that apply automatically by file type.
- Skill: on-demand domain workflow and decision guidance.
- Reference: detailed examples, rationale, matrices, and troubleshooting.
- Registry or graph: machine-readable inventory and topology.
Do not copy canonical tables or templates into an agent body.
3. Budget Context
- Apply the limits and hand-off framework in
context-optimization.instructions.md. - Keep tool lists minimal and handoffs intentional.
- Move long templates to references or templates.
- Prefer one compact structured example.
- Remove prose already supplied by an auto-loaded instruction.
- Estimate fixed cost using body bytes, matched instruction bytes, tool schemas, and mandatory skill reads.
Use the apex-context-management skill for runtime compression or debug-log audits.
Show full SKILL.md (250 more words)Show less
4. Implement Incrementally
- Update frontmatter and the smallest body section first.
- Run the focused agent validator.
- Move optional detail into references only after behavior remains valid.
- Update model registry or workflow graph mirrors when their canonical source changes.
- Update documentation when an agent or skill is added, renamed, or removed.
5. Validate
Run focused fixture tests first; they do not stage files into the active agent tree:
node --test tools/tests/lib/parse-frontmatter.test.mjs tools/tests/validate-agents/classify-model.test.mjs tools/tests/vendor-prompting/run.test.mjsAfter concurrent agent edits settle, integration checks are:
npm run validate:agents
npm run lint:vendor-prompting
npm run validate:model-consistency
npm run validate:skills
npm run lint:mdFor model changes also run npm run validate:model-catalog and
npm run validate:deprecated-models.
Output Expectations
Return:
- Files changed and ownership rationale
- Fixed-context reduction when slimming an agent
- Preserved runtime contracts and anchors
- Validation commands and results
- Any documentation or generated inventory updated
Troubleshooting
| Symptom | Action |
|---|---|
| Agent is not discovered | Validate frontmatter, filename, description form, and model syntax |
| Handoff fails validation | Verify target name, allowed fields, and input/output enrichment |
| Skill is reported orphaned | Reference .github/skills/apex-agent-authoring/SKILL.md canonically |
| Model consistency fails | Treat agent frontmatter as canonical, then update registry mirrors |
| Context remains large | Remove duplicated instruction prose and move phase-specific detail to references |
Reference Index
- Agent fleet assessment: definition scorecards and a gated remediation plan.
- .github assessment: static authoring-asset inventory and review.
- Assessment design history: reference-only, not executable.
Assessments never edit authoring assets in the review pass. Optional supplied log profiles
inform scorecards; log capture, context audit, and runtime compression remain owned by
apex-context-management.
- Agent file structure
- Authoring workflow
- Model policy
- Runtime guardrails
- Decision logging
- Skill authoring: locations, layout, loading and
contextpolicy detail.
© jonathan-vella, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 9 other files (references) in .github/skills/apex-agent-authoring of jonathan-vella/apex.
- SKILL.md
- references/agent-file-structure.md
- references/assess-agents.md
- references/assess-github-folder.md
- references/authoring-workflow.md
- references/decision-logging.md
- references/model-policy.md
- references/plan-four-layer-agent-assessment.md
- references/runtime-guardrails.md
- references/skill-authoring.md
Open the folder on GitHubat commit b8e5908
Compare with similar skills
Apex Agent Authoring 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 |
|---|---|---|---|---|---|---|
| Apex Agent Authoring this skilljonathan-vella/apex | 217 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Pydantic AI Harnesspydantic/pydantic-ai | 21k | — | ~4.9k | Automated safety check: Pass | MIT | |
| Compact Memory Implementationsimbajigege/book2skills | 183 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Deep Agentslangchain-ai/docs | 426 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Create Agent Skilloocx/tfplan2md | 174 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Discover Agenticrand/cc-polymath | 181 | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
- Official
Compact Memory Implementation
simbajigege/book2skills
A developer guide to adding compact memory to an agent: when to trigger compaction, how to fork a compactor sub-agent, what the summary holds, and how to restore it.
- Official
Deep Agents
langchain-ai/docs
Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution.
Create Agent Skill
oocx/tfplan2md
Create a new Agent Skill following project standards and templates.
Discover Agentic
rand/cc-polymath
Automatically discover agentic workflow skills when building AI agents, implementing tool use patterns, managing context windows, decomposing complex tasks, or designing multi-step autonomous…
New Resource Workflow
GoogleCloudPlatform/magic-modules
Workflow specifically for creating a new resource, supporting both autogen and manual generation.
More from jonathan-vella/apex
All 39 skills in this repoApex Azure Diagnostics
jonathan-vella/apex
WORKFLOW SKILL — Debug Azure production issues: Container Apps, Functions, App Service, AKS, VMs and messaging, with KQL log analysis.
Apex Azure Governance Discovery
jonathan-vella/apex
ANALYSIS SKILL — Azure Policy discovery: effective assignments (incl.
Apex Context Management
jonathan-vella/apex
UTILITY SKILL — Two-mode context-window management. An agent skill from jonathan-vella/apex.
Apex Python Diagrams
jonathan-vella/apex
UTILITY SKILL — Python diagram generation for Azure architectures, WAF/cost/compliance charts, ERDs, swimlanes, timelines, and wireframes.
Apex Terraform Search Import
jonathan-vella/apex
WORKFLOW SKILL — Manual-only discovery and import of existing Azure resources into Terraform management.
Apex Vendor Prompting
jonathan-vella/apex
ANALYSIS SKILL — Manual-only audit of Anthropic Claude Opus 5.5 / Sonnet 5.5 and OpenAI GPT-6 / GPT-5.6 prompting guidance and APEX conventions.
Related
Questions about Apex Agent Authoring
What does Apex Agent Authoring do?
WORKFLOW SKILL — Creates, restructures, and audits GitHub Copilot .agent.md and .prompt.md files with correct frontmatter, handoffs, model policy, context budgets, and validation. Apex Agent Authoring is an agent skill from jonathan-vella/apex.md files with correct frontmatter, handoffs, model policy, context budgets, and validation.
When should I use Apex Agent Authoring?
Apex Agent Authoring fits situations like: : routine edits covered by auto-loaded instructions; tasks that involve Building AI agents; tasks that involve Context engineering.
How do I install Apex Agent Authoring in Claude Code?
Run `npx skills add jonathan-vella/apex --skill apex-agent-authoring -a claude-code`. Or copy the skill folder (.github/skills/apex-agent-authoring in jonathan-vella/apex) into .claude/skills/apex-agent-authoring in your project. Claude Code loads it when a task matches its description.
How do I install Apex Agent Authoring in Codex?
Run `npx skills add jonathan-vella/apex --skill apex-agent-authoring -a codex`. Or copy the skill folder (.github/skills/apex-agent-authoring in jonathan-vella/apex) into .agents/skills/apex-agent-authoring in your project. Codex loads it when a task matches its description.
Can I use Apex Agent Authoring 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 jonathan-vella/apex --skill apex-agent-authoring -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/apex-agent-authoring, .gemini/skills/apex-agent-authoring, .github/skills/apex-agent-authoring and .opencode/skills/apex-agent-authoring in your project.
What does Apex Agent Authoring need to run?
Going by SKILL.md and its folder, Apex Agent Authoring needs the command-line tools its instructions call (npm and node).
Does Apex Agent Authoring access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Apex Agent Authoring safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Apex Agent Authoring use?
Apex Agent Authoring is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Apex Agent Authoring use?
About 1.8k tokens (SKILL.md is roughly 7k 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 9.6k tokens, read only when the agent opens those files.
What are the alternatives to Apex Agent Authoring?
Skills that share tags, products or a category with Apex Agent Authoring: Pydantic AI Harness (pydantic/pydantic-ai, 21k stars), Compact Memory Implementation (simbajigege/book2skills, 183 stars), Deep Agents (langchain-ai/docs, 426 stars) and Create Agent Skill (oocx/tfplan2md, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Apex Agent Authoring?
jonathan-vella (a GitHub user) maintains it in jonathan-vella/apex, which has 217 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 10, 2026.
Source: jonathan-vella/apex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.