Borrowing it
Nothing to install: this file belongs to GetKlai/klai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GetKlai/klai/main/.agents/skills/env-scope-guard/SKILL.mdgit clone --depth 1 https://github.com/GetKlai/klaiWrote 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/getklai/klai/env-scope-guard)<a href="https://agentmods.dev/skills/getklai/klai/env-scope-guard"><img src="https://agentmods.dev/badge/skills/getklai/klai/env-scope-guard.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 5.1 | $0.00058 | $0.00555 |
| Opus 5 | $0.00029 | $0.00278 |
| Sonnet 5 | $0.00012 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
env-scope-guard 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 6d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
env-scope-guard (secret scoping in compose)
deploy/check-env-file-scope.py blocks a literal bare .env under env_file in every existing deploy Compose file. It covers scalar values, quoted values, trailing comments, block lists, long list syntax (path: .env), and inline or multiline flow lists. .github/workflows/env-scope-guard.yml runs the script and its fixtures on pull requests and pushes to main; .githooks/pre-commit is the local gate.
The rule
- ❌
env_file: .env(orenv_file:+- .env) — this points at/opt/klai/.env, the merged SOPS-global file, and leaks every Klai secret into that one service's process env. One compromised service = all secrets. - ✅
env_file: ./klai-<service>/.env— per-service scoped file with only that service's secrets (REQ-6).
When adding a service
- Give it its own
deploy/klai-<service>/.envscope; register the secrets indeploy/SECRETS_MATRIX.md. - Reference only the per-service path in compose.
- Ship the secret values via
deploy/deploy.sh <service>(SOPS-decrypt + SSH) — never commit plaintext env files.
Migrating an existing service
Changing env_file: .env to a per-service file changes more than secret
visibility: values previously inherited from the merged global env can fall
back to application defaults without a startup failure.
Before the change, inventory every configured setting from the service's
settings class, Compose mapping, owning SOPS inventory, and current container.
After the change, compare the key set and value equality again. Do not print
secret values in logs or review output; compare presence and non-reversible
fingerprints where direct inspection would expose them. Investigate every
missing or changed value, including non-secret URLs and model names, before
recreating the service. A clean scope check proves only that .env is no
longer referenced; it does not prove runtime parity.
When the check fails
Run python3 -B deploy/check-env-file-scope.py locally. Scope every reported reference per service; do not add an allowlist.
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.
- 6d ago First seen · 39 lines · 58 tokens per session scan A f0b614494548
env-scope-guard is a skill published in the GitHub repository GetKlai/klai (11 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 555 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
assistant-ui-primitives
Guide for assistant-ui UI primitives - ThreadPrimitive, ComposerPrimitive, MessagePrimitive. Use when customizing chat UI components.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…