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 agentmods add instructions/jonathan-vella/apex-accelerator/agent-authoringgit 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.svg" alt="Measured on agentmods" 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 | $0.01235 | $0.01235 |
| Opus 5 | $0.00617 | $0.00617 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
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 5d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Authoring Standards
Keep this auto-loaded file limited to rules that affect runtime correctness or
repository validation. For agent creation, structural rewrites, model selection,
or deep audits, load .github/skills/agent-authoring/SKILL.md.
Frontmatter Rules
- Use valid YAML between
---delimiters with spaces, not tabs. - Keep
descriptionon one line; block scalars break agent discovery. - Keep
descriptionat or below 350 characters; aim for 300 or fewer. - Agent models use array form; prompt models use quoted string form.
- Agent frontmatter is the canonical model assignment. Mirror it in
tools/registry/agent-registry.json; catalog assignments are generated. - Use only available tool IDs. Delegation uses
agent, notagent/runSubagent. - If
agentsis present, includeagentintools. Leaf subagents setuser-invocable: falseandagents: []. - Replace deprecated
inferwithuser-invocableanddisable-model-invocation.
Complete field reference:
agent-authoring/references/agent-file-structure.md.
Frontmatter Description Length
Router descriptions need trigger keywords, not full scope documentation. Move extended scope tables into the body or an on-demand reference.
Handoff Rules
- Target an existing agent using its exact frontmatter
name. - Use only
label,agent,prompt,send,showContinueOn, andmodel. - Omit
handoffs[].modelwhen it matches the target agent's own model. - Every handoff prompt names its input and expected output.
- Use the workflow DAG rather than adding an inline handoff taxonomy.
Validation details:
workflow-engine/references/handoff-validation-rules.md.
Model Policy
Model selection is intentional. Do not change model order or assignments without explicit approval. Reasoning effort is a per-agent or per-call policy, never a model-label suffix.
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.
- 5d 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 4d ago), licensed MIT. It adds 1,235 tokens to every session, about $0.0062 per session on Opus 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
squad copilot-instructions.md
Copilot instructions for bradygaster/squad, covering copilot coding agent — squad instructions, ⚠️ identity lock — read this first, 🚦 route before you act — generic copilot sessions, adversarial input handling and team context.
vscode-unify-chat-provider AGENTS.md
Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
github-azure-agentic-journeys AGENTS.md
Instructions for DanWahlin/github-azure-agentic-journeys, covering agents and skills, journeys, prerequisites, agent & skill system and available agents.
ab100 AGENTS.md
Instructions for timothywarner-org/ab100, covering agents.md, repository purpose, source of truth, course structure and poc app.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.