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 volodchenkov/claude-sdlc-agents --skill iac-disciplinegit clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agentsWrote 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/volodchenkov/claude-sdlc-agents/iac-discipline)<a href="https://agentmods.dev/skills/volodchenkov/claude-sdlc-agents/iac-discipline"><img src="https://agentmods.dev/badge/skills/volodchenkov/claude-sdlc-agents/iac-discipline/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/volodchenkov/claude-sdlc-agents/iac-discipline"><img src="https://agentmods.dev/badge/skills/volodchenkov/claude-sdlc-agents/iac-discipline.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 | $0.00132 | $0.04477 |
| Opus 5 | $0.00066 | $0.02239 |
| Sonnet 5 | $0.00026 | $0.00895 |
| Haiku 4.5 | $0.00013 | $0.00448 |
Grade A, and why
iac-discipline 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 10d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IaC Discipline
Rule: infrastructure code is provable, not persuadable. The deliverable is not «it worked once from my laptop», it is «tofu plan in a merge request reads clean, matches the SPEC, and applies idempotently on a fresh account». Everything below exists to make that possible.
Read this skill in full before touching any infrastructure code, opening an infra MR, or reviewing an infra plan. For code style, tests, and GitOps details, cite the referenced skills — don't restate them.
Default stack (2026 modern)
Use these unless the ticket says otherwise:
| Layer | Choice | Notes |
|---|---|---|
| Provisioning | OpenTofu 1.10+ | Not Terraform. Community-standard fork since 2024. |
| Multi-env | OpenTofu Stacks | Native 1.9+ feature. Groups modules into stacks; each env is a deployment of the stack. Replaces Terragrunt's DRY layer. |
| State backend | YC Object Storage + YDB locks + KMS encryption | S3-compatible, native YC. Never local state past the bootstrap step. |
| Module registry | GitLab Terraform Module Registry (native) | Modules pinned by semver tag (version = "2.2.5"), never main, never a branch. |
| k8s app delivery | Argo CD with app-of-apps + ApplicationSet | No helm upgrade from CI. CI builds images; Argo CD syncs manifests. |
| k8s day-2 resources | Crossplane with YC provider | App teams request DBs / buckets via kubectl apply on a Claim; platform team owns Compositions. |
| Secrets | YC Lockbox + external-secrets operator | Never env vars, never k8s Secret checked in, never plain values in Helm values. |
| Cluster boot | cert-manager · external-dns · external-secrets · reloader · kyverno | Applied by Argo CD from a cluster-bootstrap/ app-of-apps. |
| Observability | VictoriaMetrics + VictoriaLogs + Grafana | VL replaced Loki by 2025 benchmarks. YC Monitoring is opt-in for small envs. |
| CI/CD auth | GitLab OIDC → YC IAM federation ($CI_JOB_JWT_V2) |
No long-lived tokens. No YCLOUD_TOKEN env var. |
| CI plan pattern | tofu plan on MR → comment; apply on merge as manual job on protected environment |
Never auto-apply on merge. Never apply from a laptop past bootstrap. |
| Version bumps | Renovate | Modules, providers, base images. Auto-MR, human-approved. |
| Security scan | checkov + tflint + trivy config | Pre-commit + CI. Blocks MR on high-severity. |
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.
- 10d ago First seen · 300 lines · 132 tokens per session scan A e0304d9ed42a
iac-discipline is a skill published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 4,477 once invoked, about $0.0007 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
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-modernization
Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.
atmos-sbom
Atmos SBOM provenance: CycloneDX and SPDX generation from vendor and Terraform evidence, coverage diagnostics, NTIA validation, and native CI workflow-artifact publication.
atmos-version
Atmos Version Tracker: version tracks, lock files, managed external dependency versions, atmos version track commands, !version, file managers, update policy, pinning, and CI verification.
atmos-cache
Atmos caching: CI cache configuration and commands, GitHub Actions cache integration, Terraform registry cache mirror/list/prune/stats/trust, and cache modernization guidance.