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/new1direction/korgex/deploying-safelynpx skills add New1Direction/korgex --skill deploying-safelygit clone --depth 1 https://github.com/New1Direction/korgexWrote 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/new1direction/korgex/deploying-safely)<a href="https://agentmods.dev/skills/new1direction/korgex/deploying-safely"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/deploying-safely.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 | $0.00020 | $0.00335 |
| Opus 5 | $0.00010 | $0.00168 |
| Sonnet 5 | $0.00004 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
deploying-safely 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.
What it actually says
A deploy is an outward-facing, hard-to-undo action. The goal is to ship often AND make a bad release boring to recover from. Confirm before deploying unless the user has clearly authorized it.
- Ship the tested artifact. Deploy the exact build CI verified — don't rebuild or hand-tweak on the way out.
- Roll out gradually. Prefer canary / staged / blue-green over flipping 100% at once. Watch the new version's health (errors, latency) before widening.
- Have a rollback ready BEFORE you ship. Know the one command/step to revert, and that the previous version still works. Rollback should be faster than forward-fix.
- Decouple deploy from release. Use feature flags so you can deploy code dark and turn behaviour on/off without a redeploy — and kill it instantly if it misbehaves.
- Backwards-compatible steps. Don't ship a code change that requires a not-yet-run migration, or drop something the old version still uses (see database-migrations' expand/contract).
- Verify after. Check health/metrics post-deploy; don't declare success on "it deployed" — declare it on "it's serving correctly" (see verify-before-done).
- If anything looks wrong, roll back first, diagnose second (see incident-response).
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 · 26 lines · 20 tokens per session scan A 5466fe2b8abf
deploying-safely is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 335 once invoked, about $0.0001 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
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.
release
Prepare a named version: preflight, version consistency, build/package, smoke test, checksums/notes, and release readiness. Publishing/tagging/deploy need separate authorization. Explicit-only.
release-notes
Use when asked to generate release notes, or when the /release-notes command runs — derive user-facing release notes from the change history since the last release.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.