Autonomous-EHS-Management AGENTS.md

Repository instructions for a safety-management website with required verification, threat-checking, and browser smoke tests. They define which roles may edit or approve work and where evidence must be recorded.

In plain words
What is it for?
Use it when modifying the EHS site, running its verification scripts, recording harness files, or following its contributor and operations workflow.
Why use it?
Safety-sensitive projects need repeatable checks and clear separation of responsibilities. These rules prevent unauthorized approval changes and make verification results traceable.

Instructions file for CodexOpenCode

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 instructions/safetymp/autonomous-ehs-management/agents-md
Clone the repo
git clone --depth 1 https://github.com/SafetyMP/Autonomous-EHS-Management

Made for: Codex, OpenCode.

Per session 1,009 This file is loaded in full into every session.
When invoked 1,009 The same file — it is already loaded in full.
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 $0.01009 $0.01009
Opus 5 $0.00504 $0.00504
Sonnet 5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 2d ago against content hash 70a521f12843, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Autonomous-EHS-Management 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 2d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Site contract

Gates

Command Purpose
./scripts/verify.sh Functional and static acceptance
./scripts/adversarial.sh Authorized local adversarial probes

Record verification_scripts as site-relative scripts/harness (exactly verify.sh and adversarial.sh). Optional wrappers may remain at scripts/verify.sh / scripts/adversarial.sh for humans; they are outside the digest boundary.

The corporate handoff fixes scope. The site manager assigns ADRs; site specialists write; the root orchestrator dispatches nondelegating workers and runs gate commands; operations excellence reviews immutable root-produced evidence. Work in isolated roots, never edit corporate approval state, and never self-approve. A site role cannot return work to corporate design; that boundary requires an explicit user rework authorization.

Site id: ehs. Prior Cursor Harness v4 is under _archives/harness-v4/.


Contributor / CI gates

Local Mirrors
npm run verify CI job verify (lint + tsc + Vitest)
./scripts/verify.sh CI verify + threat-model check
npm run verify:all verify + Playwright smoke (not full CI)
./scripts/integration-e2e.sh Same smoke path as CI e2e-smoke (before adversarial)
./scripts/adversarial.sh CI e2e-smoke adversarial step (needs a running app URL)

CI workflow .github/workflows/ci.yml runs three required jobs (pin in rulesets — see REPO_SETUP.md):

  1. supply-chain-auditnpm audit --omit=dev --audit-level=high
  2. verify — lint, tsc, Vitest
  3. e2e-smoke — Postgres migrate/seed, Playwright smoke, threat-model (PRs), adversarial probes

On trunk pushes, CI jobs release and publish run only after supply-chain-audit, verify, and e2e-smoke succeed (needs:). Production promote requires a full git SHA (not latest).

Smoke E2E (Playwright @smoke)

CI always runs signed-in smoke against service Postgres (db:migrate + db:seed:ci). Locally, signed-in specs skip unless PLAYWRIGHT_E2E_EMAIL / PLAYWRIGHT_E2E_PASSWORD are set against a migrated, seeded DB (see .env.example).

Read the full file on GitHub · 66 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. 2d ago First seen · 66 lines · 1,009 tokens per session scan A 70a521f12843

Subscribe to this mod's changes

Autonomous-EHS-Management AGENTS.md is an instructions file published in the GitHub repository SafetyMP/Autonomous-EHS-Management (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,009 tokens to every session, about $0.0050 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.