spektacular: Instructions file for Codex

AGENTS.md

spektacular AGENTS.md is an instructions file for Codex, OpenCode from jumppad-labs/spektacular. It costs 2,353 tokens per session, scanned C, original, Apache-2.0.

Repository instructions for coding agents working on the Spektacular project. They explain which rules to follow, how to handle project knowledge, and when a discussion should become a written specification.

In plain words
What is it for?
Following repository rules, saving confirmed project knowledge, recognising when conversations need specifications, and working with existing specs and plans.
Why use it?
They keep agent behavior consistent and prevent important decisions or project knowledge from being stored in the wrong place or lost during regeneration.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is jumppad-labs/spektacular's own configuration. It tells Codex and OpenCode how to work on spektacular itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spektacular configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jumppad-labs/spektacular. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jumppad-labs/spektacular/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jumppad-labs/spektacular

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for spektacular AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jumppad-labs/spektacular/agents-md.svg)](https://agentmods.dev/instructions/jumppad-labs/spektacular/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jumppad-labs/spektacular/agents-md"><img src="https://agentmods.dev/badge/instructions/jumppad-labs/spektacular/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,353 This file is loaded in full into every session.
When invoked 2,353 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02353 $0.02353
Opus 5 $0.01177 $0.01177
Sonnet 5 $0.00471 $0.00471
Haiku 4.5 $0.00235 $0.00235

Measured 8d ago against content hash 2c1ee1b43c57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

spektacular AGENTS.md scanned grade C with 1 finding 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 8d 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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

Then drive its existing steps — the "ask the user..." prompts in `templates/steps/spec/*.md` are unchanged and still apply — but answer each one from the conversation you already had instead of asking cold. For every ste
AGENTS.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Rules

@.tessl/RULES.md follow the instructions

Memory & Context

Managed by go run . init — edit templates/agents/memory-context.md in the Spektacular source, not this section in place. Hand edits will not survive the next init.

In this repository, do not persist anything to your per-user, per-machine memory store. When you would normally write to it — a learning, convention, gotcha, project fact, user preference, or anything else worth remembering between sessions — route the write through the spek-knowledge skill instead. The skill handles scope selection, search-before-write, and propose-then-confirm.

Outside this repository, continue using your per-user memory store as normal.

Spec-Worthy Discussion Recognition

Managed by go run . init — edit templates/agents/spec-trigger.md in the Spektacular source, not this section in place. Hand edits will not survive the next init.

During an open-ended discussion (diagnostics, brainstorming, exploratory back-and-forth), watch for the moment it produces something substantial enough to be worth capturing as a specification — multiple requirements mentioned, a scoped decision reached, or a feature described in enough detail that it could be built from. Don't wait to be asked; recognizing this moment and offering is your job, not the user's.

This check is not limited to live back-and-forth discussion. It applies just as much the moment you finish reading a fully-formed request — a GitHub issue, a linked ticket, a pasted design doc — that already describes a feature in spec-worthy detail. Reading a well-specified issue and going straight to implementation is the same miss as skipping the offer mid-conversation: evaluate the request against the criteria above before starting any implementation work, not only when the detail accumulates turn-by-turn in front of you.

Before deciding whether a discussion has crossed that line, read spec_trigger_threshold from .spektacular/config.yaml — check it at the moment you are deciding, not once at the start of the session, since the user may change it mid-conversation and expects that to take effect immediately. Treat a missing or absent value as "moderate". Use the configured value to calibrate how readily you offer:

Read the full file on GitHub · 158 lines

Changes

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.

  1. 8d ago First seen · 158 lines · 2,353 tokens per session scan C 2c1ee1b43c57

Subscribe to this mod's changes

spektacular AGENTS.md is an instructions file published in the GitHub repository jumppad-labs/spektacular (20 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,353 tokens to every session, about $0.0118 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens