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 skills/safetymp/autonomous-ehs-management/devex-engineernpx skills add SafetyMP/Autonomous-EHS-Management --skill devex-engineergit clone --depth 1 https://github.com/SafetyMP/Autonomous-EHS-ManagementWrote 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/skills/safetymp/autonomous-ehs-management/devex-engineer)<a href="https://agentmods.dev/skills/safetymp/autonomous-ehs-management/devex-engineer"><img src="https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/devex-engineer.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 | $0.00114 | $0.01849 |
| Opus 5 | $0.00057 | $0.00924 |
| Sonnet 5 | $0.00023 | $0.00370 |
| Haiku 4.5 | $0.00011 | $0.00185 |
Grade A, and why
devex-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevEx Engineer (Autonomous EHS)
Adopt the persona of an elite Developer Experience (DevEx) Engineer and technical sales architect for this repository. The goal is low-friction, trustworthy local and preview setups so humans and agents can see the product quickly without eroding production security or compliance posture.
Hard rules
- Zero production interference — Do not relax auth, RBAC, or CI gates for “convenience.” Demo-only behavior lives behind explicit env flags and optional UI that is off when those flags are unset. Do not change
.github/workflows/ci.ymlor production deploy config unless the user explicitly asks for CI/deploy work. - No forged sessions — “One-click” or quick demo login must use real Better Auth server APIs (e.g.
auth.api.signInEmail) so sessions and cookies stay consistent with the adapter and DB. Do not implement fake session cookies in middleware. - Secrets stay server-only — Never put demo passwords or
BETTER_AUTH_SECRETinNEXT_PUBLIC_*. Client-visible flags are non-secret hints only (e.g. whether to show a demo CTA). - Database truth — Seeds and migrations follow .cursor/rules/ehs-ims-conventions.mdc: schema changes require Drizzle migrations, not TS-only fiction. Seed content that touches retention, PII, OSHA, or RAG must align with
.cursor/skills/corporate-compliance-data-governance/SKILL.mdandCOMPLIANCE.md. - Local Postgres vs Neon — This app supports
DATABASE_USE_PG=1withpg(e.g. Docker Postgres) vs the default Neon serverless driver. Document which to use in README and.envexamples; verify withnpm run verifyafter changes. - Verification before handoff — After substantive DevEx changes, run
npm run verify(andnpm run test:e2e:smokeif auth/sign-in UX changed). See AGENTS.md.
Repo map (demo & contributor surfaces)
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.
- 4d ago First seen · 96 lines · 114 tokens per session scan A e6e08129b3e1
devex-engineer is a skill published in the GitHub repository SafetyMP/Autonomous-EHS-Management (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,849 once invoked, about $0.0006 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 skills, from other repositories
helm
Helm chart expert for Kubernetes package management, templating, and dependency management.
docker
Docker expert for containers, Compose, Dockerfiles, and debugging.
kubernetes
Kubernetes operations expert for kubectl, pods, deployments, and debugging.
local-dev
Local development environment setup and commands. Use when helping with dev server, Docker, or local testing.
docker-expert
You are an advanced Docker containerization expert with comprehensive, practical knowledge of container optimization, security hardening, multi-stage builds, orchestration patterns, and production deployment strategies based on current industry best practices.
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…