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 adtn0810/truestack --skill truestack-ci-and-deliverygit clone --depth 1 https://github.com/adtn0810/truestackWrote 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/adtn0810/truestack/truestack-ci-and-delivery)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-ci-and-delivery"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-ci-and-delivery/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/adtn0810/truestack/truestack-ci-and-delivery"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-ci-and-delivery.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 | $0.00234 | $0.02201 |
| Opus 5 | $0.00117 | $0.01100 |
| Sonnet 5 | $0.00047 | $0.00440 |
| Haiku 4.5 | $0.00023 | $0.00220 |
Grade A, and why
truestack-ci-and-delivery 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 12d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-ci-and-delivery
The path from a green PR to a running server, made boring on purpose. CI proves the change; delivery ships the exact artifact CI proved and can undo it in seconds. One self-hosted box, no autoscale — so the pipeline must be cheap, the deploy reversible, and the secrets never leave the server. Accuracy and reversibility beat clever automation.
Read project memory first — CLAUDE.md is auto-loaded (Principles + Boundaries); consult
.ai/memory/ for the existing CI provider, deploy target, image registry, branch rules, and
release tooling. Don't invent a workflow that contradicts what's recorded. If none exists,
run truestack-project-memory.
Deploys, migrations, and force-pushing tags are irreversible / data-touching — route the
design of a new pipeline or deploy strategy through truestack-architecture-planning's approval
gate before wiring it, and know that the PreToolUse gate in hooks/ will already stop a
destructive/deploy/migration command at run time (it forces a human yes). See hooks/README.md.
Where this skill sits: it owns the pipeline — encoding the checks as automated CI (it does
not replace the one-shot truestack-quality-control pass on the current change; it makes those checks run
on every PR), the release/versioning, and the deploy step that gates and triggers a release.
The on-box cutover mechanics (nginx reload, container swap, SIGTERM drain, the rollback runbook)
belong to truestack-deploy-and-runtime; authoring the migration DDL/backfill belongs to
truestack-database-migrations; a cron trigger inside a workflow lives here, but scheduling an
assistant/agent run is truestack-task-scheduling.
1. Pipeline stages — fast, required, in order
On every PR run the cheap gates first so failures surface in seconds: lint → type-check → unit tests → build. Fail fast, run independent jobs in parallel, and keep the whole PR run under a few minutes so the box (and the team) isn't waiting. Build the deployable artifact in CI, not on the server — the server only pulls what CI proved.
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.
- 12d ago First seen · 110 lines · 234 tokens per session scan A 5c2b44df6d2e
truestack-ci-and-delivery is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 234 tokens to every session and 2,201 once invoked, about $0.0012 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
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
github-actions-templates
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
deployment-pipeline-design
Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use this skill when designing zero-downtime deployment pipelines, implementing canary rollout strategies, setting up multi-environment promotion workflows, or debugging failed deployment gates in CI/CD.
gitlab-ci-patterns
Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.