Borrowing it
Nothing to install: this file belongs to tbvjvsladla/easy_vllm_simulator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tbvjvsladla/easy_vllm_simulator/single-node/.agents/skills/upstream-version-watch/SKILL.mdgit clone --depth 1 https://github.com/tbvjvsladla/easy_vllm_simulatorWrote 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/tbvjvsladla/easy_vllm_simulator/upstream-version-watch)<a href="https://agentmods.dev/skills/tbvjvsladla/easy_vllm_simulator/upstream-version-watch"><img src="https://agentmods.dev/badge/skills/tbvjvsladla/easy_vllm_simulator/upstream-version-watch/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/tbvjvsladla/easy_vllm_simulator/upstream-version-watch"><img src="https://agentmods.dev/badge/skills/tbvjvsladla/easy_vllm_simulator/upstream-version-watch.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 | $0.00023 | $0.00092 |
| Opus 5.5 | $0.00009 | $0.00037 |
| Sonnet 5.5 | $0.00005 | $0.00018 |
| Haiku 4.5 | $0.00002 | $0.00009 |
Grade A, and why
upstream-version-watch 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 6d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- assets/build_plane/Dockerfile.source-build-upstage 9.9 KB
- assets/build_plane/model_inputs/configs/exaone45-33b.sh 1.6 KB runs code
- assets/build_plane/model_inputs/configs/exaone45-33b.yaml 1.3 KB
- assets/build_plane/model_inputs/configs/hy3.sh 2.8 KB runs code
- assets/build_plane/model_inputs/configs/hy3.yaml 7.4 KB
- assets/build_plane/model_inputs/envs/.env.exaone45-33b 1.2 KB
- assets/build_plane/model_inputs/envs/.env.hy3 2.9 KB
- assets/configs/arm_patch.sh 2.5 KB runs code
- assets/configs/debug-init.sh 1.1 KB runs code
- assets/configs/serve_runner.sh 8.4 KB runs code
- assets/current-production-resolution.json 4.0 KB
- assets/source_port/source-sm12x-port-vllm-0.27.0/resolutions.json 12 KB
- assets/source_port/source-sm12x-port-vllm-0.27.0/resolutions.patch 14 KB
- assets/source_port/source-sm12x-port-vllm-0.27.1/resolutions.json 12 KB
- assets/source_port/source-sm12x-port-vllm-0.27.1/resolutions.patch 14 KB
- config.example.yaml 1.8 KB
- failure_patterns.yaml 3.8 KB
- fixtures/cluster_env_dgx-spark-gb10.golden 594 B
- fixtures/nccl_env_dgx-spark-gb10.golden 1.5 KB
- fixtures/version_delta_0.27.0_to_0.27.1.golden.json 26 KB
- fixtures/version_delta_negative_unknown_plane.fixture.json 26 KB
- references/failure-recovery.md 3.0 KB
- references/multinode-build.md 7.6 KB
- references/native_wheelhouse_accept.json 2.9 KB
- references/resolve-and-render.md 13 KB
- references/source-build.md 18 KB
- scripts/budget_preflight.py 33 KB runs code
- scripts/check_smoke_model.py 26 KB runs code
- scripts/check_spec_layout.py 9.1 KB runs code
- scripts/classify_failure.py 3.7 KB runs code
- scripts/closing_sequence.sh 22 KB runs code
- scripts/container_inventory.sh 6.0 KB runs code
- scripts/fetch_sub_docs.sh 11 KB runs code
- scripts/judge_version_delta.py 49 KB runs code
- scripts/layer_ledger.py 68 KB runs code
- scripts/multinode_comms_smoke.sh 10 KB runs code
- scripts/multinode_serve_smoke.sh 108 KB runs code
- scripts/native_multinode_serve.py 128 KB runs code
- scripts/native_wheelhouse.py 85 KB runs code
- scripts/push_branches.py 24 KB runs code
- scripts/regen_build_patches_src.py 27 KB runs code
- scripts/regen_requirements.py 6.4 KB runs code
- scripts/render_dockerfile.py 106 KB runs code
- scripts/render_native_triplet.py 22 KB runs code
- scripts/resolve_build_track.py 10 KB runs code
- scripts/resolve_ngc_tag.py 5.8 KB runs code
- scripts/resolve_torch_pin.py 3.8 KB runs code
- scripts/resolve_wheel.py 4.9 KB runs code
- scripts/selftest_branch_sync.py 51 KB runs code
- scripts/single_serve_down.sh 16 KB runs code
- scripts/single_serve_up.sh 25 KB runs code
- scripts/slave_forward.py 41 KB runs code
- scripts/smoke_clone.sh 19 KB runs code
- scripts/sync_branches.sh 53 KB runs code
- scripts/sync_to_sub.sh 172 KB runs code
- scripts/validate_runtime_patch.py 4.0 KB runs code
- templates/docker-compose.multi.template.yaml 12 KB
- templates/docker-compose.single.template.yaml 3.3 KB
- templates/Dockerfile.source-build-dsv4.template 18 KB
- templates/Dockerfile.source-build.template 21 KB
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.
- 6d ago Changed · -217 lines · -123 tokens per session ce1004b2aefb
- 1mo ago Changed 171cb9995456
- 1mo ago Changed · +4 lines 79ff3dc6bc7b
- 1mo ago Changed · +29 lines ed5d941501fc
- 1mo ago Changed · +47 lines 060a9d5085a7
- 2mo ago Changed · +15 lines b056804ea3f2
- 2mo ago First seen · 129 lines · 146 tokens per session scan A cdabe1889f29
upstream-version-watch is a skill published in the GitHub repository tbvjvsladla/easy_vllm_simulator (22 stars, last pushed 4d ago), with no licence file. It adds 23 tokens to every session and 92 once invoked, about $0.0001 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.
upstream-version-watch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| upstream-version-watchtbvjvsladla/easy_vllm_simulator | Skill | 22 | 4d ago | none | A | 23 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |