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/sravanskumar/mace/claude-mdgit clone --depth 1 https://github.com/sravanskumar/maceWrote 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/sravanskumar/mace/claude-md)<a href="https://agentmods.dev/instructions/sravanskumar/mace/claude-md"><img src="https://agentmods.dev/badge/instructions/sravanskumar/mace/claude-md.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 | $0.01263 | $0.01263 |
| Opus 5 | $0.00632 | $0.00632 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
mace CLAUDE.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 3d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MACE — Context for AI Assistants
This file gives Claude (and other AI tools) concise context when working in this repository.
What MACE is
MACE (MCP-Assisted Content Enforcement) is an MCP server that enforces regional content governance on Adobe Experience Manager (AEM) using native AEM APIs only (no custom AEM code). It is used from Claude Desktop or Cursor: users run natural-language prompts that map to tools (list pages, scan violations, list styles, fix violations). Governance rules are defined in a JSON file; the server resolves policies from page templates when not explicitly set.
Tech stack
- Runtime: Node.js 18+
- Language: TypeScript (compiled to
dist/) - Protocol: Model Context Protocol (MCP), stdio transport
- AEM: HTTP only — QueryBuilder, Sling GET (.infinity.json), Sling POST. No Maven, no custom AEM bundles.
Repository layout
| Path | Purpose |
|---|---|
src/index.ts |
MCP server entry; registers 5 tools and routes CallTool to handlers. |
src/governance-config.ts |
Loads and parses governance-rules.json; rule/component lookup; no restart needed for rule changes. |
src/aem-client.ts |
HTTP client for AEM (GET/POST); uses .env for URL and credentials. |
src/template-policy-resolver.ts |
Resolves Content Policy path from page template (cq:template → policies → component mapping). |
src/policy-styles.ts |
Fetches policy styles (cq:styleGroups) and resolves style label ↔ ID. |
src/tools/*.ts |
One file per tool: list-pages, list-violations, list-styles, update-style, fix-violations. |
governance-rules.example.json |
Example governance rules (v1.1 schema). Users copy to governance-rules.json (gitignored). |
.env |
AEM URL, credentials, timeouts; loaded from project root. Not committed. |
scripts/run-acceptance.cjs |
Acceptance script that calls tool handlers against a live AEM (requires AEM + .env). |
docs/MACE-UseCase-Architecture.pdf |
Architecture and setup documentation. |
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.
- 3d ago First seen · 68 lines · 1,263 tokens per session scan A 49d652989b2f
mace CLAUDE.md is an instructions file published in the GitHub repository sravanskumar/mace (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,263 tokens to every session, about $0.0063 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 2026-08-31.
Other instructions, from other repositories
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
xcstrings-crud CLAUDE.md
Instructions for Ryu0118/xcstrings-crud, covering xcstrings-crud, build & test, architecture, code style and key files.
arty AGENTS.md
Instructions for tleyden/arty, a project described as: iOS realtime voice assistant w/ translation + connectors.
kiwiki AGENTS.md
AGENTS.md instructions for natorus87/kiwiki, covering projekt-anweisungen, projekt-kontext, verbindliche lokalisierungsregel, regeln (automatisch geladen via .codex/rules/) and verfügbare sub-agenten.
kiwi-paper GEMINI.md
Instructions for hletrd/kiwi-paper, covering kiwi-paper — gemini cli instructions, 사용법, 4단계 파이프라인, 지원 문서 유형 (12종) and 핵심 규칙.
PixelPilot uiux-i18n-routing.instructions.md
URL structure for multiple languages with Next.js, Laravel, and Vue Router. Includes language switcher without full page reload.