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-operating-frame.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-operating-frame)<a href="https://agentmods.dev/instructions/jonathan-vella/apex-accelerator/agent-operating-frame"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/agent-operating-frame/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-operating-frame"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/agent-operating-frame.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 | $0.00611 | $0.00611 |
| Opus 5.5 | $0.00244 | $0.00244 |
| Sonnet 5.5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
apex-accelerator agent-operating-frame.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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Frame
An authoring applyTo match does not prove runtime attachment. Keep essential constraints in the agent body.
Native interaction
Every directly selected main can use actual ask_user for material missing inputs.
Requirements, Architect, Design and Governance retain their interactive discovery/clarification role.
Batch independent fields, validate freeform values and reuse current answers.
Native requestedSchema contains only properties; root type, required and additionalProperties
are not tool parameters. Direct ask_user receives only message and requestedSchema.
Delegated envelopes keep unresolved names outside the schema in needed_inputs.
Delegated mains return a stable USER_INPUT_REQUIRED form to the interactive parent and stop the phase.
Leaves never ask users, delegate or manage parent todos.
An absent question tool blocks a required decision; no guessed defaults or terminal prompts.
Native Autopilot can answer questions; a form return is not independent human authorization.
Scope and current evidence
- Load only current-phase skills/references, reuse available unchanged sections and recover missing required guidance after source changes, compaction or a new chat.
- Recover project state through
apex-recall show <project> --json; no direct state JSON reads/writes. A file inventory is not artifact content or approval evidence. - Respect domain ownership/frozen inputs and actual governance/security. Return drift to its owner, not an inline upstream replacement.
- User instructions outrank skill style/workflow choices, not security/governance/approval requirements. Name the path and exact blocking requirement when relevant.
- Validate written non-Markdown shapes and actual commands before passing results. Markdown artifact validation follows the designated Git/review owner.
Native tasks
Use explicit scope, inputs, outputs and failure criteria in actual native task prompts. Consume actual results and only supported same-task handles; one-shot tasks are not universally resumable. No worker-ready turn, custom execution envelope, per-worker log gate or handoff-button dependency. The graph defines domain prerequisites/owners, not permission or native UI transitions. Runtime hooks are retired and must not be restored.
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 · -31 lines · -443 tokens per session 38f6b4dbaef0
- 27d ago Changed · +14 tokens per session b8be31fd53b8
- 1mo ago Changed · +1 lines · +38 tokens per session a64cc6cacf56
- 1mo ago Changed · -21 lines · -228 tokens per session edfb6af5d344
- 1mo ago First seen · 106 lines · 1,230 tokens per session scan A 67801531504b
apex-accelerator agent-operating-frame.instructions.md is an instructions file published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 611 tokens to every session, about $0.0024 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.