agentmods.dev

LAZYANTIGRAVITY: Instructions file for Claude Code

AGENTS.md

LAZYANTIGRAVITY AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from daeryundf2-prog/LAZYANTIGRAVITY. It costs 2,162 tokens per session, scanned A, original, MIT.

Repository instructions for the LAZYANTIGRAVITY code project. They describe its coding rules, technology stack, special work modes, test commands, and forbidden actions.

In plain words
What is it for?
Use them when asking an agent to work on LAZYANTIGRAVITY and follow its conventions, testing process, and restrictions.
Why use it?
They give a coding agent the project-specific rules it needs before changing files or running tests.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PostToolUse hook event, but also the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

This is daeryundf2-prog/LAZYANTIGRAVITY's own configuration. It tells Claude Code, Codex and OpenCode how to work on LAZYANTIGRAVITY 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 LAZYANTIGRAVITY configures →

not rated 14repo changed 23d ago A scan 2,162 tokens original MIT
View source ↗ daeryundf2-prog/LAZYANTIGRAVITY
Reuse

Borrowing it

Nothing to install: this file belongs to daeryundf2-prog/LAZYANTIGRAVITY. 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/daeryundf2-prog/LAZYANTIGRAVITY/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/daeryundf2-prog/LAZYANTIGRAVITY

Made for: Claude Code, 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 LAZYANTIGRAVITY AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daeryundf2-prog/lazyantigravity/agents-md/github.svg)](https://agentmods.dev/instructions/daeryundf2-prog/lazyantigravity/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/daeryundf2-prog/lazyantigravity/agents-md"><img src="https://agentmods.dev/badge/instructions/daeryundf2-prog/lazyantigravity/agents-md/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.

agentmods 80×15 button for LAZYANTIGRAVITY AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/daeryundf2-prog/lazyantigravity/agents-md"><img src="https://agentmods.dev/badge/instructions/daeryundf2-prog/lazyantigravity/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,162 This file is loaded in full into every session.
When invoked 2,162 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02162 $0.02162
Opus 5.5 $0.00865 $0.00865
Sonnet 5.5 $0.00432 $0.00432
Haiku 4.5 $0.00216 $0.00216

Measured 23d ago against content hash 346865e1945c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LAZYANTIGRAVITY AGENTS.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 23d 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.

AGENTS.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Conventions

Conventions for human contributors and AI agents working on this repository.

Stack

  • Node >=20 runtime.
  • npm workspaces (root package.json) — all components live under components/*.
  • TypeScript 6 strict mode.
  • Biome 2 linting and formatting.

Omniscient Mode & Two-Step Strike

  • Trust level: 프롬프트 계약(advisory). The items below are behavioral guidance, not mechanically enforced rules. Implementation is scripts/awt-guard.mjs injecting fixed advisory phrases (additionalContext) plus a regex that detects meta-excuse phrases — it advises, it cannot guarantee.
  • Assume Agent Correctness: Proceed decisively in Omniscient Mode without second-guessing routine actions.
  • Eliminate Attention Dispersion: Avoid wandering into unrelated files out of self-doubt.
  • Two-Step Strike: High-focus generation + mechanical error capture (PostToolUse hooks & Oracles).
  • AWT Trajectory Lock: Lock to the task contract. If an action drifts by 1 degree, trim and realign immediately.
  • Anti-Metacognitive Ban: Never emit self-excusing meta-dialogue ("흥미롭군요", "That's interesting"). Emit factual error stacks and fixes only.
  • Coverage claims require an audit receipt: Any "전수/100% 커버리지" style audit conclusion must be backed by node scripts/coverage_audit.mjs --source <원문파일> --target <산출물…> --json <receipt.json>. Save the source material to a file BEFORE auditing; auditing against a self-made keyword list is a circular audit and is forbidden — the tool refuses to run without --source. The receipt keeps a per-item source-line → target-location mapping. (GUARD_PACK_VERSION 1.0.0, canonical: lazyforensic)

Claim-Evidence Enforcement

Capability and completion claims are mechanically gated — report registered / loadable / verified honestly:

  • scripts/stop_claim_guard.mjs (Stop/SubagentStop hook): blocks final messages that assert completion or capability ("완료", "전수", "즉시 사용 가능", "immediately usable", "완벽히 동일", …) with no falsifiable evidence (command output, test counts, artifact path, commit SHA). It also fact-retraces claimed artifact paths against disk and rejects stale/zero-byte receipts.
  • scripts/awt-guard.mjs (PreToolUse): emits a CLAIM EVIDENCE advisory when capability-assertion phrasing appears in tool payloads, demanding the three-tier report (registered ≠ usable).
  • scripts/lazyantigravity-doctor.mjs (runtime section): probes the PATH-resolved lazyantigravity/omo binaries for the subcommands skills actually invoke (research-claims, create-goals, status). A stale shadow binary that answers with a usage fallback is recorded per-capability; doctor warns only when no binary serves the capability.
  • scripts/check-keyword-skills.mjs (node scripts/check-keyword-skills.mjs [AGENTS.md ...]): resolves every $name referenced by keyword tables to a real skill file or reference — dangling registrations fail the run. Also flags the same trigger keyword routed in multiple rows (keyword-collision) and files with no table at all (no-table) so a vacuous pass is visible. Pass consuming-workspace AGENTS.md files as arguments — the plugin repo's own AGENTS.md intentionally has no routing table.
  • scripts/check-skill-links.mjs: resolves every relative markdown link under skills/ — docs must not reference files that were never shipped.
  • scripts/check-skills-drift.mjs (npm run audit:skills-drift, wired into npm run check): byte-exact audit of every file under skills/ against its source (shared-skills or component skill). A "shared↔skills 무결성/1바이트" claim is only valid while this reports zero drift — it also catches unsourced runtime artifacts (e.g. __pycache__) left in the materialized tree.
  • scripts/check_contract_drift.mjs (npm run audit:contract-drift, wired into npm run check): verifies vendored contracts/ files against PIN.json SHA-256 pins — manual edits to pinned contracts fail the run.
  • scripts/claim-patterns.mjs: single source for the capability-claim regex shared by awt-guard and stop_claim_guard — extend it there once, not in two places.

Read the full file on GitHub · 97 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. 23d ago Changed · +1 lines · +63 tokens per session 346865e1945c
  2. 24d ago Changed · -15 tokens per session e82f524b7969
  3. 1mo ago Changed · +4 lines · +262 tokens per session b0183dc39c32
  4. 1mo ago Changed · +12 lines · +470 tokens per session a477130d63ae
  5. 1mo ago Changed · +4 lines · +213 tokens per session 77566a604882
  6. 1mo ago Changed · -5 tokens per session bfff8d104fae
  7. 1mo ago Changed · +7 lines · +172 tokens per session 89895accbc65
  8. 1mo ago First seen · 69 lines · 1,002 tokens per session scan A 8a908e9cc981

Subscribe to this mod's changes

LAZYANTIGRAVITY AGENTS.md is an instructions file published in the GitHub repository daeryundf2-prog/LAZYANTIGRAVITY (14 stars, last pushed 7d ago), licensed MIT. It adds 2,162 tokens to every session, about $0.0086 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.

TypeScriptagentic-codingai-agentautomationdeveloper-toolslazycodex
Related

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).

microsoft/vscode · 9,715 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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

vscode model-prompts.instructions.md

Model-specific prompt authoring and registry guidelines.

microsoft/vscode · 2,022 tokens