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/notque/vexjoy-agent/dev-branch-deploynpx skills add notque/vexjoy-agent --skill dev-branch-deploygit clone --depth 1 https://github.com/notque/vexjoy-agentWrote 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/notque/vexjoy-agent/dev-branch-deploy)<a href="https://agentmods.dev/skills/notque/vexjoy-agent/dev-branch-deploy"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/dev-branch-deploy.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 | $0.00076 | $0.01990 |
| Opus 5 | $0.00038 | $0.00995 |
| Sonnet 5 | $0.00015 | $0.00398 |
| Haiku 4.5 | $0.00008 | $0.00199 |
Grade A, and why
dev-branch-deploy 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 2d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev-Branch Deploy — Hermes & Maia
Test a Hermes or Maia stack change in a live lab region before merging to master, using the
pipeline's parallel dev lane. One workflow, two stacks — parametrized by stack.
The problem this solves
Concourse pins a git branch: per resource at pipeline-definition time; you can't override it at
trigger time. So normally you must merge to master to see a chart/secrets change run in a lab.
The dev lane adds a second set of jobs pointed at <stack>-dev-branch, so you deploy and validate
in a real lab region with no risk to master or production.
Stack parameters
Everything below is identical between stacks except these values.
| Param | hermes | maia |
|---|---|---|
| Dev branch | hermes-dev-branch |
maia-dev-branch |
| fly target | ci-monitoring |
monitoring |
| Concourse | https://ci1.eu-de-2.cloud.sap |
https://ci.eu-de-2.cloud.sap |
| Pipeline dir | ci/hermes/ in cc/secrets |
ci/maia/ in cc/secrets |
set-pipeline vars |
— | --load-vars-from vars.yaml |
| Chart | openstack/hermes |
openstack/maia |
Constants (both stacks):
- Team:
monitoring - Lab regions the dev lane deploys to:
qa-de-1,qa-de-2,qa-de-3,eu-de-3 - Repos the dev branch must exist on:
cc/secrets(GHEgithub.wdf.sap.corp) andsapcc/helm-charts(github.com) - Local
cc/secretsclone:~/gh/secrets
The two lanes
| Lane | Branch | Role |
|---|---|---|
labs |
master |
Guards production-branch health. Never break it. |
dev |
<stack>-dev-branch |
Sandbox: validate a feature in a real lab before master. |
Both deploy to the same lab regions, independently. Production lanes (bronze/silver/gold/global)
are untouched by this workflow.
Pipeline wiring (reference)
Dev lane = paired git resources + a dev job group.
secrets-dev.git→<stack>-dev-branch(twin ofsecrets.giton master)helm-charts-dev.git→<stack>-dev-branch(twin ofhelm-charts.giton master)- Shared by both lanes: built image,
kube-secrets, credentials.
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.
- 2d ago First seen · 177 lines · 76 tokens per session scan A 59d970350999
dev-branch-deploy is a skill published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,990 once invoked, about $0.0004 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
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
latex-submission-pipeline
Use when building a LaTeX manuscript submission pipeline with templates, latexmk, BibTeX/Biber, chktex, latexindent, CI PDF builds, compile debugging, and submission zip packaging.
squid-implement-night
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan.
ci
Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI). Triggers: CI setup, build pipeline, GitHub Actions config, debug CI, GitLab CI.
squid-review-ci
Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE. Output: a CI-validated feature PR. Trigger after /squid-review passes.
azure-devops
Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…