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 vinhnx/VTCode --skill crate-opsgit clone --depth 1 https://github.com/vinhnx/VTCodeWrote 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/vinhnx/vtcode/crate-ops)<a href="https://agentmods.dev/skills/vinhnx/vtcode/crate-ops"><img src="https://agentmods.dev/badge/skills/vinhnx/vtcode/crate-ops/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/vinhnx/vtcode/crate-ops"><img src="https://agentmods.dev/badge/skills/vinhnx/vtcode/crate-ops.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 | $0.00062 | $0.00945 |
| Opus 5.5 | $0.00025 | $0.00378 |
| Sonnet 5.5 | $0.00012 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
crate-ops 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crate Ops
Any harness (Muse, Claude Code, Codex, VT Code, human) can run this workflow. It is the procedure, not the runner: a Muse executable version lives at .agents/workflows/crate-ops.js, but the steps below are the source of truth.
The core trap: feature-unification masking
A workspace-wide build (cargo check, ./scripts/check-dev.sh) unifies features across all default members. A crate can compile there while its own manifest is broken: a missing features = ["..."] declaration only surfaces when the crate builds alone (cargo check -p <crate>), in a restricted CI command, or during cargo publish verification (which rebuilds the packaged tarball). Real case: vtcode depended on vtcode-core with default-features = false and no explicit tui, so the binary failed with 145 errors everywhere except the default workspace build.
Workflow
1. Orient
- Read root
AGENTS.mdand each touched crate'sAGENTS.md. - Read the touched manifests plus every dependent's declaration of the changed crate (
grep -rn '<crate-name>' --include=Cargo.toml crates/ Cargo.toml, excludingtarget/). - Check
git logon the manifests for intent behinddefault-features = falseor version pins.
2. Reproduce in isolation
Reproduce with the crate alone, never with a workspace-wide build:
cargo check --locked -p <crate>
Match the failure against the reported one (same crate, same error class/count) before changing anything.
3. Fix
- Keep changes surgical: only touch files the change owns.
- When a crate needs an optional feature of a dependency, declare it explicitly on that dependency edge. Precedent (
fuzz/Cargo.toml, rootCargo.toml):vtcode-core = { path = "...", version = "...", default-features = false, features = ["tui"] } - Keep path+version on all workspace path dependencies; never rely on unification from other members.
- Follow repo rules:
anyhow::Resultwith context, nounwrap/expect/panicin production code, workspace lints apply. Do not commit unless asked.
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.
- 2d ago First seen · 57 lines · 62 tokens per session scan A cb8042f24fea
crate-ops is a skill published in the GitHub repository vinhnx/VTCode (907 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 945 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 2026-11-11.
crate-ops compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crate-opsvinhnx/VTCode | Skill | 907 | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| uniflyhyperb1iss/unifly | Skill | 276 | 6d ago | Apache-2.0 | A | 63 | Claude Code |
| uniflyhyperb1iss/unifly | Skill | 276 | 6d ago | Apache-2.0 | A | 63 | Claude Code |
| rust-doctorarthjean/rust-doctor | Skill | 23 | 4d ago | Apache-2.0 | A | 49 | Claude Code, Codex |
| ratatui-tuistyrene-lab/omegon | Skill | 48 | today | none | A | 38 | Claude Code, Codex |
| m07-concurrencykikakkz/wait-agent | Skill | 24 | 2d ago | none | A | 75 | Claude Code |
| rust-learnerkikakkz/wait-agent | Skill | 24 | 2d ago | none | A | 123 | Claude Code |