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 S3YED/appie-kit --skill cron-env-isolation-guardgit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/cron-env-isolation-guard)<a href="https://agentmods.dev/skills/s3yed/appie-kit/cron-env-isolation-guard"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/cron-env-isolation-guard/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/s3yed/appie-kit/cron-env-isolation-guard"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/cron-env-isolation-guard.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 | $0.00045 | $0.00669 |
| Opus 5 | $0.00023 | $0.00334 |
| Sonnet 5 | $0.00009 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
cron-env-isolation-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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cron Env Isolation Guard
Why this exists
macOS launchd strips most shell environment from launched jobs. Variables available in an interactive terminal are NOT inherited. Common silent failures:
- API key env var missing → CLI crashes immediately
- OAuth keyring prompt has no TTY → deadlock
- MCP plugins init on claude startup → hang → SIGKILL after watchdog timeout
Diagnostic checklist (run in order)
- Check exit code:
launchctl list | grep <label>— column 2 is last exit code.-1/1= crash;-15= SIGTERM (watchdog?). - Check log size: if stdout log = 0 or ~90 bytes, job started but didn't produce output → silent crash or early hang.
- Read the log: check stderr path from the plist. Look for:
no TTY available for keyring file backend password prompt→ add the keyring password to plist EnvironmentVariables.invalid_grant/Bad Request→ OAuth token expired; need interactive re-auth.aes.KeyUnwrap(): integrity check failed→ encrypted token corrupted; need re-auth.- Python traceback / CLI crash → missing API key in env.
- MCP plugin startup messages followed by silence + SIGKILL → add
--no-mcptoclaude -pinvocation.
- Read the plist: confirm which EnvironmentVariables are set. Compare against what the script needs interactively.
- Run the script manually with the same PATH the plist specifies:
PATH=<plist-PATH> <command>. Compare output.
Common fixes
| Symptom | Fix |
|---|---|
| Keyring/password prompt has no TTY | Add password env var to plist EnvironmentVariables dict |
| OAuth expired (invalid_grant) | Re-auth interactively, then reload launchd job |
| CLI crash (no API key) | Add API key to plist env |
claude -p hangs on MCP init |
Add --no-mcp flag to the claude invocation |
| Any env var missing | Add to plist EnvironmentVariables OR source a .env file at script start |
Applying plist fixes
# Edit the plist to add env vars, then reload:
launchctl unload ~/Library/LaunchAgents/<label>.plist
launchctl load ~/Library/LaunchAgents/<label>.plist
# Verify:
launchctl list | grep <label>
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.
- 9d ago First seen · 55 lines · 45 tokens per session scan A 563b61f41438
cron-env-isolation-guard is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 17d ago), licensed MIT. It adds 45 tokens to every session and 669 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
agentic-process-monitor
Monitor background processes from Claude Code using sentinel files, heartbeat liveness, and subagent polling. Best practices and.
code-hardcode-audit
Detect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.