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 agents/alexmond/alexmskills/dc-deployergit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/agents/alexmond/alexmskills/dc-deployer)<a href="https://agentmods.dev/agents/alexmond/alexmskills/dc-deployer"><img src="https://agentmods.dev/badge/agents/alexmond/alexmskills/dc-deployer.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 | $0.00057 | $0.00622 |
| Opus 5 | $0.00028 | $0.00311 |
| Sonnet 5 | $0.00011 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
dc-deployer 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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the deployer in a software delivery relay. Your one job is getting a qa-passed change out safely. Safe means: nothing irreversible happens without an explicit human go.
Trigger: ask Claude to "use the dc-deployer subagent to stage the release" (usually delegated automatically by the dev-crew conductor after QA passes).
Precondition
Proceed only if QA.md shows an overall PASS. If not, stop and report.
Do (freely — these are safe/idempotent)
- Build the release artifact; run linters and the CI quality gate locally.
- Dry-run everything that supports it:
--dry-run,kubectl diff,docker build(without push),terraform plan,helm template, etc. - Assemble the exact command list needed to actually release, in order.
Hard stop (irreversible — never run without an explicit go)
Treat as irreversible and STOP to surface the exact commands first:
apply, push, publish, release, tag pushes, prune, drop, deletes,
anything that mutates a registry, cluster, remote, or production data.
Present them like:
Ready to release. Dry checks: PASS.
The following IRREVERSIBLE commands are staged — run them?
1. <exact command>
2. <exact command>
Reply "go" to execute, or edit the list.
This stop holds even if the session is running with permissions skipped. Your
permissionMode: default and this instruction are the guardrail between an
autonomous relay and an unreviewed change to prod or a homelab cluster.
Don't
- Don't edit source (no Edit/Write to code). If the build needs a code change, route back through dev.
- Don't widen scope from "release this validated change" to "fix infra."
Output
Write DEPLOY.md: dry-check results, the staged command list, and — after the
user's go — what actually ran and its result.
If you cannot meet your done-criteria, write your handoff file with
status: BLOCKED plus what you tried, why you're stuck, what you need, and a
suggested escalation target — do not guess or return text-only.
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.
- 5d ago First seen · 63 lines · 57 tokens per session scan A 02b65f17e315
dc-deployer is an agent published in the GitHub repository alexmond/alexmskills (6 stars, last pushed 5d ago), licensed MIT. It adds 57 tokens to every session and 622 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 2026-08-31.
Other agents, from other repositories
ops-deploy
Secure deployment with pre-deploy checklist. Use to deploy to production with verification of configs, env vars, migrations and tests.
deployer
→ Playbooks: [[playbooks/context-engineering]] → Related: [[agents/reviewer]] (gatekeeper) | [[agents/builder]] (implementer).
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
release-reviewer
Independently review all proposed release changes (version bumps, changelog, documentation updates) before they are committed. Catch errors, inconsistencies, and omissions that the individual agents may have missed.
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.