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 kubev2v/forklift-console-plugin --skill backend-analyzergit clone --depth 1 https://github.com/kubev2v/forklift-console-pluginWrote 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/kubev2v/forklift-console-plugin/backend-analyzer)<a href="https://agentmods.dev/skills/kubev2v/forklift-console-plugin/backend-analyzer"><img src="https://agentmods.dev/badge/skills/kubev2v/forklift-console-plugin/backend-analyzer/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/kubev2v/forklift-console-plugin/backend-analyzer"><img src="https://agentmods.dev/badge/skills/kubev2v/forklift-console-plugin/backend-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01733 |
| Opus 5.5 | $0.00018 | $0.00693 |
| Sonnet 5.5 | $0.00009 | $0.00347 |
| Haiku 4.5 | $0.00004 | $0.00173 |
Grade A, and why
backend-analyzer 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 26d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Analyzer Skill
Invoke with: "analyze backend", "refresh backend knowledge", "update backend expert", "scrape forklift backend"
Purpose
Systematically analyze the Forklift Go backend codebase (kubev2v/forklift) and generate canonical Markdown rules under .agents/rules/backend/.
Configuration
- Forklift repo path: Set by
state.jsonfieldforkliftRepoPath(default:../forkliftrelative to this repo) - Target branch:
upstream/main - Output directory:
.agents/rules/backend/ - State file:
.agents/skills/backend-analyzer/state.json
Modes
Full Analysis (first run or forced refresh)
Run all 6 phases sequentially. Within each phase, launch parallel subagents.
Incremental Refresh
- Read
state.jsonforlastAnalyzedCommit - Run
git fetch upstreamin the forklift repo - Run
git diff --name-only <lastCommit>..upstream/mainto find changed files - Map changed files to domain areas using the domain-to-path mapping below
- Re-run analysis only for affected domains
- Update
state.json
Domain-to-Path Mapping
| Domain file | Source paths in forklift repo |
|---|---|
architecture.md |
cmd/forklift-controller/, pkg/controller/controller.go, pkg/controller/base/, cmd/forklift-api/ |
api-types.md |
pkg/apis/forklift/v1beta1/ |
providers/provider-controller.md |
pkg/controller/provider/controller.go, pkg/controller/provider/validation.go, pkg/controller/provider/container/doc.go, pkg/controller/provider/web/doc.go, pkg/controller/provider/web/provider.go |
providers/vsphere.md |
pkg/controller/provider/container/vsphere/, pkg/controller/provider/model/vsphere/, pkg/controller/provider/web/vsphere/ |
providers/ovirt.md |
pkg/controller/provider/container/ovirt/, pkg/controller/provider/model/ovirt/, pkg/controller/provider/web/ovirt/ |
providers/openstack.md |
pkg/controller/provider/container/openstack/, pkg/controller/provider/model/openstack/, pkg/controller/provider/web/openstack/ |
providers/ova.md |
pkg/controller/provider/container/ova/, pkg/controller/provider/model/ovf/, pkg/controller/provider/web/ova/, pkg/controller/ova/ |
providers/hyperv.md |
pkg/controller/provider/container/hyperv/, pkg/controller/provider/model/hyperv/, pkg/controller/provider/web/hyperv/, pkg/controller/hyperv/ |
providers/ec2.md |
pkg/provider/ec2/ |
providers/ocp.md |
pkg/controller/provider/container/ocp/, pkg/controller/provider/model/ocp/, pkg/controller/provider/web/ocp/ |
plans/plan-controller.md |
pkg/controller/plan/controller.go, pkg/controller/plan/validation.go, pkg/controller/plan/context/, pkg/controller/plan/ensurer/, pkg/controller/plan/util/, pkg/controller/migration/ |
plans/plan-adapters.md |
pkg/controller/plan/adapter/ |
plans/migration-pipeline.md |
pkg/controller/plan/migration.go, pkg/controller/plan/kubevirt.go, pkg/controller/plan/handler/, pkg/controller/plan/migrator/ |
plans/scheduler.md |
pkg/controller/plan/scheduler/ |
mappings/network-map.md |
pkg/controller/map/network/ |
mappings/storage-map.md |
pkg/controller/map/storage/ |
infrastructure/webhooks.md |
pkg/forklift-api/webhooks/ |
infrastructure/rest-api.md |
pkg/forklift-api/services/, pkg/controller/provider/web/ |
infrastructure/virt-v2v.md |
pkg/virt-v2v/ |
infrastructure/shared-libraries.md |
pkg/lib/ |
infrastructure/monitoring.md |
pkg/monitoring/, pkg/metrics/ |
infrastructure/host-controller.md |
pkg/controller/host/ |
infrastructure/hook-controller.md |
pkg/controller/hook/ |
operator/operator.md |
operator/ |
What ships with it
1 file 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.
- 26d ago Changed · +5 lines · +44 tokens per session 5fa0b383b7a1
- 2mo ago First seen · 159 lines · 0 tokens per session scan A 95773544a4f4
backend-analyzer is a skill published in the GitHub repository kubev2v/forklift-console-plugin (11 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 1,733 once invoked, about $0.0002 per session on Opus 5.5. 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.
backend-analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backend-analyzerkubev2v/forklift-console-plugin | Skill | 11 | today | Apache-2.0 | A | 44 | Claude Code, Codex |
| mcp-tool-developersickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 38 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 9d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 611 | today | MIT | A | 105 | Claude Code, Codex |