A lightweight system for adding structured comments and named code regions that explain how important parts of a project fit together. GRACE means Graph-RAG Anchored Code Engineering, and its markup helps machines navigate code.

Use it to initialize or continue GRACE markup, expose public APIs, and review code that uses GRACE markers or purpose comments.

It makes the purpose and boundaries of non-trivial code clearer during setup, maintenance, and review.

grace-lite — Skill for Codex by knopki/agent-skills

Install

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.

Any agent

npx skills add knopki/agent-skills --skill grace-lite

Clone the repo

git clone --depth 1 https://github.com/knopki/agent-skills

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/knopki/agent-skills/grace-lite/github.svg)](https://agentmods.dev/skills/knopki/agent-skills/grace-lite)

Your own site

<a href="https://agentmods.dev/skills/knopki/agent-skills/grace-lite"><img src="https://agentmods.dev/badge/skills/knopki/agent-skills/grace-lite/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/knopki/agent-skills/grace-lite"><img src="https://agentmods.dev/badge/skills/knopki/agent-skills/grace-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,159 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.02159
Opus 5.5	$0.00019	$0.00864
Sonnet 5.5	$0.00009	$0.00432
Haiku 4.5	$0.00005	$0.00216

Measured 2mo ago against content hash ed4492e2527c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

grace-lite 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (assets/_semantic_template_reference.js, assets/_semantic_template_reference.py, assets/_semantic_template_reference.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/grace-lite/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graph-RAG Anchored Code Engineering, lite variant

Overview

GRACE gives a project semantic code markup — region-based contracts and anchors that make code machine-navigable, documentation inside the code.

Also, GRACE methodology offers Log Driven Development as observable contracts.

When to Use

The user asks to initialize a project with GRACE markup (activation trigger: "GRACE init") - follow the references/init.md.
The user asks to continue / resume adding GRACE markup to a project that was already started - follow the references/init.md.
The user asks to review - follow the references/review.md.
You are working with code with word PURPOSE in comments.

Markup Reference

Principles

Mark up all public and non-trivial code.
Expose public API explicitly via language features: __all__ in Python, export in JS/TS, etc.
Markup must be proportional to the code's complexity.
Python exception: if an entity is annotated by markup, it must always be wrapped in a region (unlike C#, where short top-level entities may use /// <purpose> without #region).
For exact comment syntax, refer to the template in _semantic_template_reference.* files in assets directory.

See Common Pitfalls for the corresponding anti-patterns.

Workflow

MODULE_CONTRACT first — always write the module contract before any code. It sets the boundary and purpose of the file.
Public contracts next — define contracts for all public classes, functions, and methods. Create stubs.
Implement — write code inside the contracted regions.

Region Types

MODULE_CONTRACT

File-level contract. Exactly one per file, placed at the very top before all code.

Defines what the module is for and how it relates to the rest of the system.

Fields:

PURPOSE — required. The goal of the module: what business/operational need it fulfills.
SCOPE — recommended. Functional areas covered by the module and what is explicitly excluded (NOT:).
INVARIANTS — recommended. Conditions or states that always hold.
USECASES — optional. Scenarios in [Entity]: [Actor] => [Action] => [Goal] format.
DEPENDENCIES — optional. Non-trivial dependencies: USES API:, READS:, WRITES:.
RATIONALE — optional. Q/A format: why it was implemented this way.
KEYWORDS — optional. Comma-separated keywords for grep search.

Read the full file on GitHub · 229 lines

Files

What ships with it

14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 229 lines · 47 tokens per session scan A ed4492e2527c

Subscribe to this mod's changes

grace-lite is a skill published in the GitHub repository knopki/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 2,159 once invoked, about $0.0002 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 2026-08-31.

Building agents

grace-lite next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
grace-liteknopki/agent-skills	Skill	2	3d ago	MIT	A	47	Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code