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 gnana997/bumper --skill gating-terraform-plansgit clone --depth 1 https://github.com/gnana997/bumperWrote 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/gnana997/bumper/gating-terraform-plans)<a href="https://agentmods.dev/skills/gnana997/bumper/gating-terraform-plans"><img src="https://agentmods.dev/badge/skills/gnana997/bumper/gating-terraform-plans/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/gnana997/bumper/gating-terraform-plans"><img src="https://agentmods.dev/badge/skills/gnana997/bumper/gating-terraform-plans.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 | $0.00080 | $0.00712 |
| Opus 5 | $0.00040 | $0.00356 |
| Sonnet 5 | $0.00016 | $0.00142 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
gating-terraform-plans 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gating Terraform plans with bumper
bumper is a Terraform/OpenTofu plan safety gate. Run it before every apply. It
needs the bumper CLI on PATH (https://github.com/gnana997/bumper). If bumper is
not installed, do not apply destructive changes — tell the user to install it.
Workflow
Follow these steps in order. Never skip the scan, and never apply while high/critical findings stand.
-
Produce a plan file:
terraform plan -out plan.tfplan terraform show -json plan.tfplan > plan.json(OpenTofu:
tofu plan/tofu show -json.) -
Scan it:
bumper plan.jsonAdd
--explainfor plain-English detail, or--format jsonfor machine-readable findings. Exit codes: 0 = clean, 1 = findings present, 2 = usage error. -
Triage by severity:
- critical / high → STOP. Do not apply. Go to step 4.
- medium / low → review; proceed only if each finding is understood and acceptable.
-
Fix → re-scan loop (repeat until clean or every finding is consciously accepted): a. Edit the
.tfto remove the hazard or narrow its blast radius. b. Re-runterraform plan -out plan.tfplan && terraform show -json plan.tfplan > plan.json. c.bumper plan.json. d. If findings remain, return to (a). -
Record a verdict so the apply is unblocked:
bumper verify plan.tfplanThis scans the saved plan and, on a pass, writes a sha256-bound verdict. To accept a reviewed risk explicitly:
bumper verify --accept plan.tfplan. -
Apply the exact plan you verified:
terraform apply plan.tfplan
Why verify the .tfplan, not the JSON
The verdict is bound to the plan file's sha256. bumper's apply-guard hook blocks
terraform apply for any plan that has not been verified — so applying a different
or re-generated plan is rejected until you verify it. Never apply a plan you have
not scanned.
Example
Asked to "add an S3 bucket and apply":
terraform plan -out plan.tfplan && terraform show -json plan.tfplan > plan.jsonbumper plan.json→ HIGH:aws_s3_buckethas no public-access block.- Add
aws_s3_bucket_public_access_block, re-plan, re-scan → clean. bumper verify plan.tfplan→ verdict recorded.terraform apply plan.tfplan.
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 · 75 lines · 80 tokens per session scan A b85ab03d84f4
gating-terraform-plans is a skill published in the GitHub repository gnana997/bumper (2 stars, last pushed 18d ago), licensed Apache-2.0. It adds 80 tokens to every session and 712 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 2026-08-31.
Other skills, from other repositories
ccmanager-config
Set up, review, or repair a CCManager config — .ccmanager.json at a git repository root, or the global /.config/ccmanager/config.json. Use when someone wants ccmanager to launch a different agent CLI (codex, gemini, cursor-agent, copilot…), add command presets, run a command on session state changes or worktree…
performing-sca-dependency-scanning-with-snyk
This skill covers implementing Software Composition Analysis (SCA) using Snyk to detect vulnerable open-source dependencies in CI/CD pipelines. It addresses scanning package manifests and lockfiles, automated fix pull request generation, license compliance checking, continuous monitoring of deployed applications, and…
microsoft-typescript
TypeScript is a language for application scale JavaScript development. ALWAYS use when editing or working with .ts, .tsx, .mts, .cts files or code importing "typescript". Consult for debugging, best practices, or modifying typescript, TypeScript.
sindresorhus-log-update
Log by overwriting the previous output in the terminal. Useful for rendering progress bars, animations, etc. ALWAYS use when writing code importing "log-update". Consult for debugging, best practices, or modifying log-update, log update.
performing-sca-dependency-scanning-with-snyk
This skill covers implementing Software Composition Analysis (SCA) using Snyk to detect vulnerable open-source dependencies in CI/CD pipelines. It addresses scanning package manifests and lockfiles, automated fix pull request generation, license compliance checking, continuous monitoring of deployed applications, and…
jfrog
Interact with the JFrog Platform via the JFrog CLI, JFrog MCP server and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search…