Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pulumi/agent-skillsnpx agentmods add skills/pulumi/agent-skills/upstream-patchesWrote 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/pulumi/agent-skills/upstream-patches)<a href="https://agentmods.dev/skills/pulumi/agent-skills/upstream-patches"><img src="https://agentmods.dev/badge/skills/pulumi/agent-skills/upstream-patches/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/pulumi/agent-skills/upstream-patches"><img src="https://agentmods.dev/badge/skills/pulumi/agent-skills/upstream-patches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 106 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00058 | $0.01352 |
| Opus 5 | $0.00029 | $0.00676 |
| Sonnet 5 | $0.00012 | $0.00270 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
upstream-patches 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 11d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstream Patches
upstream/ is a git submodule pointing to the upstream Terraform provider. patches/ contains patch files applied on top of it. Use ./scripts/upstream.sh to manage patch state.
Default Behavior
- If fixing a regression introduced by an existing patch, amend the owning patch commit.
- Do not create a new patch unless the user explicitly asks.
Commands Reference
| Command | Description |
|---|---|
./scripts/upstream.sh init |
Initialize upstream and apply patches to working directory |
./scripts/upstream.sh init -f |
Destructively discard checkout/rebase state and re-initialize upstream |
./scripts/upstream.sh checkout |
Create branch with patches as commits for editing |
./scripts/upstream.sh rebase -i |
Interactively edit patch commits |
./scripts/upstream.sh rebase -o <commit> |
Rebase patches onto a new upstream commit |
./scripts/upstream.sh check_in |
Write commits back to patches and exit checkout mode |
Guardrails
- Never commit directly to
upstream/withoutcheckout/check_in. - Direct edits under
upstream/outside checkout are ephemeral duringupgrade-provider; the tool resets submodule state. - Do not hand-edit
patches/*.patchunless intentionally doing raw patch surgery. - Prefer non-interactive rewrite flow over interactive rebase for agents.
Find Owning Patch First
Before editing patch content, identify the owning patch/commit.
./scripts/upstream.sh checkout
# Find candidate patch files by touched file path or unique hunk text
rg -n "path/to/file|unique_symbol" patches/*.patch
# Optional: inspect candidate patch header/hunks
sed -n '1,120p' patches/00NN-Example.patch
# Map patch file to commit in upstream checkout branch
patch=patches/00NN-Example.patch
subject=$(sed -n 's/^Subject: \[PATCH\] //p' "$patch" | head -n1)
cd upstream
git log --oneline pulumi/patch-checkout --grep "$subject"
# If needed, disambiguate by touched path
git log --oneline pulumi/patch-checkout -- path/to/file
cd ..
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 173 lines · 58 tokens per session scan A 56a593f44d1b
upstream-patches is a skill published in the GitHub repository pulumi/agent-skills (68 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 1,352 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 2026-08-30.
Other skills, from other repositories
infra-as-code
Manage infrastructure in version control so it's reviewable, reproducible, and rollback-able. Invoke when provisioning new infra or cleaning up ad-hoc resources.
infrastructure-as-code-guardian
Universal Infrastructure as Code (IaC) agent skill for authoring, securing, and managing cloud infrastructure across Terraform, Pulumi, CloudFormation, Ansible, and Bicep. Provides cross-tool security hardening, state management best practices, cost optimization, drift detection, and CI/CD integration. Covers AWS…
commit
Git commit workflow with precommit hook handling, lint/type checking, README updates, and API reference updates. Use when the user wants to commit changes. Handles precommit hooks that modify files (formatting, linting) by re-staging and retrying. Runs ruff lint and pyright type checks on staged Python files, and…
update-pr
Update an existing pull request with new changes. Use when the user wants to update a PR, push follow-up changes to a PR, refresh a PR description, or sync a PR with latest commits. Triggers on: update pr, update-pr, update the pr, push to pr, refresh pr, sync pr, update pull request.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
next-step
Change-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree. Not for: executing the suggested command (user decides), auto-loop decisions (hooks handle that). Output: findings-based suggestions or session summary with commit seed.