Borrowing it
Nothing to install: this file belongs to jonathan-vella/apex-accelerator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jonathan-vella/apex-accelerator/main/.github/instructions/agent-authoring.instructions.mdgit clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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/instructions/jonathan-vella/apex-accelerator/agent-authoring)<a href="https://agentmods.dev/instructions/jonathan-vella/apex-accelerator/agent-authoring"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/agent-authoring/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/instructions/jonathan-vella/apex-accelerator/agent-authoring"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/agent-authoring.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 | $0.00970 | $0.00970 |
| Opus 5.5 | $0.00388 | $0.00388 |
| Sonnet 5.5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
apex-accelerator agent-authoring.instructions.md 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 6d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Authoring Standards
Target Copilot inside VS Code. The authoring skill contains optional detailed guidance; do not load its whole reference tree during production work.
Frontmatter and native tools
- Use valid YAML, available tool IDs and concise descriptions.
- Active definitions omit model/effort pins; descriptive catalogs and legacy fixture pins remain compatible.
- Every user-invocable main explicitly includes native
ask_user. Requirements, Architect, Design and Governance ask material questions when directly selected. - Nonempty
agentsrequires theagentcapability. Leaf workers are hidden,agents: [], without question, delegation or parent-todo tools. - Orchestrator, Deploy, Diagnose and manual Challenger disable implicit model invocation. This source policy is not proof of enforced routing or credential isolation.
- Active agents do not declare UI
handoffs. The owner observed no controls with Probe Source selected in Copilot; native task results/explicit role selection are the supported APEX design. Historical handoff fixtures remain compatibility data, not production requirements. - Never restore the intentionally retired repository runtime hooks.
Body and interaction
Keep essential role, goal, success, scope, output and stop rules in the body. Use concise Markdown, actual phase inputs/outputs and progressively loaded domain references. Do not merely relocate the old complete body to a reference to claim optimization. Source length is not a measurement of runtime tokens, latency or quality.
Use explicit caller execution_mode: direct|delegated and actual calling context.
Direct selection invokes ask_user with message and requestedSchema.properties;
batch independent fields, validate freeform answers and reuse current decisions.
Delegated mains return USER_INPUT_REQUIRED, stable request_id, phase and form to the parent.
Leaves return their role-specific input failure. No terminal questions or default owner answers.
Cancel stops; decline never approves. Autopilot may auto-answer, so form/task output is not
independent human signoff, Azure scope or risk-owner authorization.
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.
- 6d ago Changed · -65 lines · -731 tokens per session 1f8bd9d5b3bf
- 14d ago Changed · +2 lines · +50 tokens per session c3214e28513c
- 17d ago Changed · -1 tokens per session 0d087cc9be42
- 27d ago Changed · +4 lines · +87 tokens per session a86f973c6de7
- 1mo ago Changed · -2 lines · +11 tokens per session 4fb7a4d39c81
- 1mo ago Changed · +19 lines · +319 tokens per session dc941738592a
- 1mo ago First seen · 128 lines · 1,235 tokens per session scan A b88deaa879bf
apex-accelerator agent-authoring.instructions.md is an instructions file published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 970 tokens to every session, about $0.0039 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.