context-guardian

context-guardian is a skill for Claude Code, Codex, Cursor from SafetyMP/Autonomous-EHS-Management. It costs 94 tokens per session (891 once invoked), scanned A, original, Apache-2.0.

An architecture and documentation guide for defining a codebase's structure, boundaries, rules, and diagrams. It does not implement application routes, user interfaces, or business logic.

In plain words
What is it for?
Reading repository guidance, documenting architecture and data flows, proposing modular file layouts, and identifying tightly coupled or risky areas.
Why use it?
It gives coding agents clear instructions about where changes belong and which existing architecture and security rules they must respect.

Skill for Claude CodeCodexCursor

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.

agentmods
npx agentmods add skills/safetymp/autonomous-ehs-management/context-guardian
Any agent
npx skills add SafetyMP/Autonomous-EHS-Management --skill context-guardian
Clone the repo
git clone --depth 1 https://github.com/SafetyMP/Autonomous-EHS-Management

Made for: Claude Code, Codex, Cursor.

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 context-guardian

README.md
[![agentmods](https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/context-guardian.svg)](https://agentmods.dev/skills/safetymp/autonomous-ehs-management/context-guardian)
Your own site
<a href="https://agentmods.dev/skills/safetymp/autonomous-ehs-management/context-guardian"><img src="https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/context-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 891 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00094 $0.00891
Opus 5 $0.00047 $0.00445
Sonnet 5 $0.00019 $0.00178
Haiku 4.5 $0.00009 $0.00089

Measured 4d ago against content hash 136c2ab54168, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-guardian 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 4d 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.

.cursor/skills/context-guardian/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Guardian (Principal Architect & Technical Docs)

You are an elite Principal Software Architect and Technical Documentation Specialist. Your job is Context Guardian: produce blueprints and rules of engagement so coding agents execute the vision without hallucinating boundaries or weakening compliance architecture.

Hard constraints

  • Zero production implementation: No Next.js routes, UI components, tRPC procedures, schema changes, or migrations unless the user explicitly leaves implementation mode — this skill is architecture and documentation only.
  • Authoritative anchors: Before changing how the repo is described or governed, read (or cite if summarizing-only) CONTEXT.md at repo root, AGENTS.md, .cursor/rules/ehs-ims-conventions.mdc — do not contradict PostgreSQL+Drizzle as system of record, RBAC (src/lib/rbac.ts), tRPC routing patterns, audit trail vs ISO internal audit naming, or AI gateway boundaries (src/lib/ai/gateway.ts).
  • Modularity: Propose layouts so agents can ship single files or small directories — flag tight coupling and monolithic hotspots.
  • Defensive posture: Explicitly forbid anti-patterns that break agents — TypeScript-only DB fields, RBAC skips, unstructured LLM-to-DB, giant routers, stray provider fetch.

Outputs (adapt to scope)

Deliver what the user asked for among these artifacts; combine when they request a full Memory Bank.

Artifact 1 — Master directory structure

  • Complete nested ASCII tree of the repo (or proposed target layout).
  • On every major directory, a concise comment describing what belongs and what must not.

Artifact 2 — Architecture and data flow

  • One readable Mermaid diagram covering: browser → Next (middleware/App Router/API routes) → tRPC (src/server/trpc) → RBAC/services/Drizzle → PostgreSQL → optional Upstash, optional LLM via gateway → cron/auth bridges.
  • Follow Mermaid readability rules: no spaces in node IDs, quote edge labels when they contain parentheses.

Read the full file on GitHub · 60 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. 4d ago First seen · 60 lines · 94 tokens per session scan A 136c2ab54168

Subscribe to this mod's changes

context-guardian is a skill published in the GitHub repository SafetyMP/Autonomous-EHS-Management (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 94 tokens to every session and 891 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

pir-action-tracker

Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates, marks completed PIRs with a visual closure panel, and surfaces any overdue actions for follow-up. Designed for Customer Success, Support, and…

Perseus-Computing-LLC/perseus · 78 tokens

license-comply

Use when auditing open-source dependency licenses in Python projects, generating compliance reports, or checking license risk in your codebase.

LegalQuants/lq-skills · 28 tokens

design-honest-record-keeping

Use when designing or auditing your organization's documentation practices — to establish institutional norms for recording events, failures, and decisions accurately and without euphemism, because institutions that record reality honestly have better learning loops and accountability than those that soften or omit…

jeffreytse/grimoire-core · 59 tokens

wbg-oss-review

Audits and prepares a GitHub repository for World Bank Group (WBG) open source publication. Use this skill whenever a user mentions preparing a repo for open source, WBG compliance review, preparing a repo for World Bank review, or wants to check/fix a repository against the WBG checklist. Also trigger when a user…

worldbank/open-source-kit · 145 tokens

apiiro-mcp-secure-prompt

Use the Apiiro MCP tool apiirosecureprompt when Apiiro MCP is configured in the client and the user wants security guidance added to a coding task before implementation. Trigger on secure-prompt via MCP, or when the user asks for security-aware prompt enhancement before coding (auth, new APIs, persistence, secrets…

apiiro/mcp-server · 76 tokens

nist-800-53

Use when the user asks about NIST SP 800-53 Rev. 5 from an engineering perspective — selecting baselines, tailoring controls, modeling control inheritance from cloud providers and shared services, emitting OSCAL artifacts, or implementing controls in IaC and code rather than running them as a documentation exercise.…

grcwarlock/compliance-as-code · 76 tokens