Infra Sandboxed Apply
The SANDBOX-APPLY-CONVERGENCE-PROCEDURE (feat-foundry-infra-live-seam-sandboxed-apply) — an UNATTENDED, real `tofu apply` in a THROWAWAY sandbox account followed by a post-apply convergence proof (`apply -> re-plan == ∅`), originally designed to emit a dedicated `sandbox-apply` walk-evidence surface for the since-retired bespoke merge gate (see the DORMANT note). EXPLICIT CLI ORCHESTRATION (never native `tofu test`, which is opaque — no saved plan / `-detailed-exitcode` / plan-JSON): `tofu init` (throwaway backend) -> resolve the applying identity from the OpenTofu PROVIDER''s OWN `aws_caller_identity` in the SAME provider config that applies (NEVER a sidecar `aws` CLI) -> `decide_sandbox_apply` (pure, fail-closed; REFUSE unless the provider-evaluated id is a `^\d{12}$` member of the committed `.foundry/sandbox-accounts.json` allowlist, no provider credential override, posture==EXECUTE, the policy gate passes, and the pre-apply plan is non-empty) -> arm the crash-backstop `tofu destroy` trap BEFORE any mutation -> `plan -out=planfile -lock-timeout=120s` -> `show -json planfile` -> the MANDATORY policy gate over the saved plan (absent/error/fail all REFUSE, no ack escape) -> `apply -lock-timeout=120s planfile` (exit≠0 partial-apply is a COMPUTED FAIL, not a crash) -> `show -json > state.json` (coverage) -> `plan -out=replan` -> `show -json replan` -> assert convergence (exit-0 AND an empty parsed resource-change set, via the shipped `foundry_plan_model.parse_actions_detail`) -> an EXPLICIT captured `tofu destroy` (its real exit sets the recorded `teardown` status; runs on GREEN, convergence-FAIL, AND apply-FAIL) -> `emit_infra_walk_evidence` on every computed outcome. Composes with — never re-builds — the shipped posture gate + SoD execute/generate split (`foundry_id_apply`): the sandboxed apply IS the EXECUTE branch bound to the sandbox account; prod always stays `GENERATE_RUNBOOK`. ADVISORY craft procedure FOR the trusted operator — it does NOT gate, approve, or merge; the merge floor (the adopter''s branch protection + CI, docs/merge-floor.md) is the merge authority. CURRENTLY DORMANT (named honestly): the `decide_sandbox_apply`/`emit_infra_walk_evidence` primitives this procedure drives, and its drop-in doctor selftest, were not shipped (no surviving implementation) in scripts/ — this SKILL.md is design intent for a re-implementation against the current floor (ci.yml + btb-gates), not a live procedure today.
Security AStatic scan found no risk patternsHow grading works ›
From the source SKILL.md
The shipped read-only infra live-seam (the retired infra live-seam atom) proves tofu plan == ∅ against already-applied infrastructure. That answers "is the codified state converged right now", never "does this change actually apply cleanly and then converge". This skill is the SANDBOX-APPLY-CONVERGENCE-PROCEDURE: it runs an unattended, real tofu apply in a throwaway sandbox account, then proves the post-apply state is a fixed point — a re-plan that must be empty — and was designed to emit the proof on a dedicated sandbox-apply walk-evidence surface consumed by the since-retired bespoke merge…
What this skill does
Infra Sandboxed Apply is a community-contributed Claude Code skill in the backend sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/infra-sandboxed-apply/ and loads when your prompt matches the skill's trigger.
Who uses this skill
The Infra Sandboxed Apply Claude Code skill is built for software engineers, backend developers, full-stack teams, and technical leads building and maintaining production systems. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 176,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
How to install
Free
Manual install (2 steps)
mkdir -p ~/.claude/skills/infra-sandboxed-apply
curl -L https://claudskills.com/skills/infra-sandboxed-apply/SKILL.md \
-o ~/.claude/skills/infra-sandboxed-apply/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/infra-sandboxed-apply/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/infra-sandboxed-apply/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\infra-sandboxed-apply\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Telegram
📱 Install from your phone or desktop Telegram
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
Pro
One-click install via the desktop app
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
Frequently asked questions
How do I install the Infra Sandboxed Apply Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy
SKILL.md from the source repository to
~/.claude/skills/infra-sandboxed-apply/SKILL.md and restart Claude Code. Both flows are detailed at
claudskills.com/install/.
What does the Infra Sandboxed Apply skill do?
The SANDBOX-APPLY-CONVERGENCE-PROCEDURE (feat-foundry-infra-live-seam-sandboxed-apply) — an UNATTENDED, real `tofu apply` in a THROWAWAY sandbox account followed by a post-apply convergence proof (`apply -> re-plan == ∅`), originally designed to emit a dedicated `sandbox-apply` walk-evidence surface for the since-retired bespoke merge gate (see the DORMANT note). EXPLICIT CLI ORCHESTRATION (never native `tofu test`, which is opaque — no saved plan / `-detailed-exitcode` / plan-JSON): `tofu init` (throwaway backend) -> resolve the applying identity from the OpenTofu PROVIDER''s OWN `aws_caller_identity` in the SAME provider config that applies (NEVER a sidecar `aws` CLI) -> `decide_sandbox_apply` (pure, fail-closed; REFUSE unless the provider-evaluated id is a `^\d{12}$` member of the committed `.foundry/sandbox-accounts.json` allowlist, no provider credential override, posture==EXECUTE, the policy gate passes, and the pre-apply plan is non-empty) -> arm the crash-backstop `tofu destroy` trap BEFORE any mutation -> `plan -out=planfile -lock-timeout=120s` -> `show -json planfile` -> the MANDATORY policy gate over the saved plan (absent/error/fail all REFUSE, no ack escape) -> `apply -lock-timeout=120s planfile` (exit≠0 partial-apply is a COMPUTED FAIL, not a crash) -> `show -json > state.json` (coverage) -> `plan -out=replan` -> `show -json replan` -> assert convergence (exit-0 AND an empty parsed resource-change set, via the shipped `foundry_plan_model.parse_actions_detail`) -> an EXPLICIT captured `tofu destroy` (its real exit sets the recorded `teardown` status; runs on GREEN, convergence-FAIL, AND apply-FAIL) -> `emit_infra_walk_evidence` on every computed outcome. Composes with — never re-builds — the shipped posture gate + SoD execute/generate split (`foundry_id_apply`): the sandboxed apply IS the EXECUTE branch bound to the sandbox account; prod always stays `GENERATE_RUNBOOK`. ADVISORY craft procedure FOR the trusted operator — it does NOT gate, approve, or merge; the merge floor (the adopter''s branch protection + CI, docs/merge-floor.md) is the merge authority. CURRENTLY DORMANT (named honestly): the `decide_sandbox_apply`/`emit_infra_walk_evidence` primitives this procedure drives, and its drop-in doctor selftest, were not shipped (no surviving implementation) in scripts/ — this SKILL.md is design intent for a re-implementation against the current floor (ci.yml + btb-gates), not a live procedure today.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Infra Sandboxed Apply skill?
Use Infra Sandboxed Apply when your Claude Code task falls under the Engineering category — specifically in the backend area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Infra Sandboxed Apply" or describe the task and let Claude pick). Browse related skills at
/category/engineering/.
What is a Claude Code skill and how does the Infra Sandboxed Apply skill fit in?
A Claude Code skill is a
SKILL.md file that lives under
~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Infra Sandboxed Apply is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Engineering category. Learn more at
/learn/what-is-a-claude-skill/.
Attribution & license
Cite this skill
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
APA
lukasrepublic. (2026). Infra Sandboxed Apply [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/infra-sandboxed-apply/
BibTeX
@misc{infra-sandboxed-apply-2026,
author = {lukasrepublic},
title = {Infra Sandboxed Apply [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/infra-sandboxed-apply/}
}
Embed this skill
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Badge
[](https://claudskills.com/skills/infra-sandboxed-apply/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/infra-sandboxed-apply.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/infra-sandboxed-apply.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Infra Sandboxed Apply"></iframe>
Security scan
Grade A · scanned 2026-08-05 — free static scan against the OWASP Agentic Skills Top 10.
No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›
- ✓ Prompt injection
- ✓ Data exfiltration
- ✓ Supply chain
- ✓ Reverse shell
- ✓ Credentials
- ✓ Execution
- ✓ Filesystem
- ✓ Persistence
- ✓ Obfuscation
- ✓ Network
Show this grade on your repo (click to copy):
[](https://claudskills.com/skills/infra-sandboxed-apply/#security)
More Engineering skills
Browse all Engineering skills in the ClaudSkills registry, or explore these other picks from the same category:
Part of Acreator Store — Adam Lankamer's AI tools:
PerfectStudio ·
Ucaption ·
UTagger ·
AutoXPoster ·
TestYourSkills ·
AutomationFlows ·
Au Naturel ·
Telegram @acreatorstore