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 skills add randommonicle/claude-skills --skill env-change-verificationgit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/env-change-verification)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/env-change-verification"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/env-change-verification/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/randommonicle/claude-skills/env-change-verification"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/env-change-verification.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00110 | $0.00665 |
| Opus 5 | $0.00055 | $0.00332 |
| Sonnet 5 | $0.00022 | $0.00133 |
| Haiku 4.5 | $0.00011 | $0.00067 |
Grade A, and why
env-change-verification 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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Env-change verification
Cross-repo: an entire iOS build track silently talked to the wrong Supabase backend because
the cloud build could not see .env.local and nobody diffed the CI variables; a Railway
value stored as KEY=value served a malformed URL; Netlify functions read old values until
the next deploy.
The rule
Setting a variable and the running artifact using it are two separate steps, and presence is not correctness. After any env change: know the variable's read time, complete the step that makes it live, and verify from the live surface.
How to apply
- Know the read time per variable. Build-time-baked (
VITE_*,import.meta.env, anything bundled) needs a rebuild; deploy-baked (serverless env) needs a redeploy; request-time-read needs nothing — the proposal's own flag conventions depend on knowing which is which. - CI and cloud builds never see
.env.local. Whenever a build consumes build-time vars, diff the CI variable set against the canonical local env — name by name AND value by value. - Validate the value, not its presence: the right project ref (not the sibling
project's), no
KEY=prefix pasted into a value field, a URL that parses. A wrong-but-present value fails silently; a missing one at least crashes. - Verify from the live surface — hit the endpoint, open the built app — never from the dashboard that shows what you just typed.
- Adding a secret can activate a previously-skipped CI job that needs more than that one secret; watch the next run.
- Module-load env reads make pure code un-importable (a CI red at import, before any test body, is the signature) and crash the process on a missing var — prefer lazy initialisation of external clients.
What this skill does not do
It does not cover schema changes (db-migration-verification) or feature-flag semantics beyond their read-time. It does not replace one-real-ride — a ride after an env change is still the final gate.
Why
Config is the only layer where a change can be "successfully saved" and have no effect at all, indefinitely, with no error anywhere. Evidence: ASH LESSONS_LEARNED 2026-05-27 (evening), 2026-06-04 (night), and the CLAUDE.md Railway section; ICC L-018 and its CLAUDE.md review-requests note.
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.
- 11d ago First seen · 51 lines · 110 tokens per session scan A 84024b945586
env-change-verification is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 110 tokens to every session and 665 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.