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 OutlineDriven/outline-driven-development --skill cargo-workflowsgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/cargo-workflows)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/cargo-workflows"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cargo-workflows/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/outlinedriven/outline-driven-development/cargo-workflows"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cargo-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 28 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00029 | $0.01283 |
| Opus 5 | $0.00015 | $0.00642 |
| Sonnet 5 | $0.00006 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
cargo-workflows 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 3d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cargo workflows
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user manages a Cargo workspace, sets feature flags, writes a build.rs script, configures CI caching, runs cargo nextest, audits dependencies, or updates Cargo.lock. |
| Authority | Reversible local: writes only local Cargo.toml, build.rs, Cargo.lock, CI workflow files, and report files the user names; rollback is git checkout -- or git reset for tracked files and rm for new reports. No remote mutation. |
| Side effect | Local Cargo.toml, workspace, build.rs, CI, and lock files may change; guidance and command output go to chat. |
| Done | The requested Cargo workflow builds or runs cleanly, or the failing command and its cause are reported. |
Inputs
- The project path (required): the workspace root or member crate.
- The task (required): workspace setup, feature flags, build script, CI caching,
cargo nextest, dependency audit, orCargo.lockmanagement. - Rust version (optional): defaults to 1.98.1 with edition 2024.
- Target crate or feature names (optional): used for scoped builds, tests, and updates.
- CI platform (optional): GitHub Actions, GitLab CI, or local runner.
Procedure
- Identify the project and toolchain. Run
rustc --versionandcargo --version. Locate the workspace root by finding theCargo.tomlthat contains[workspace]or the root package. Done when: the toolchain version and the workspace root are known. - Workspace setup. If the task is workspace setup, create or edit the root
Cargo.tomlwith[workspace],members,resolver = "2",[workspace.dependencies], and[workspace.package]. In memberCargo.toml, inherit withversion.workspace = trueandedition.workspace = true. For pattern details, seereferences/workspace-patterns.md. Done when:cargo check --workspacesucceeds. - Feature flags. If the task is feature flags, configure
[features]in the memberCargo.toml. Keep features additive, usedep:optional_depsyntax for optional dependencies, and setresolver = "2". Verify withcargo check --no-default-featuresandcargo check --all-features. Done when: the requested feature combinations build cleanly. - Build scripts (
build.rs). If the task is build scripts, add or editbuild.rsat the crate root. Emitcargo:rerun-if-changed=...,cargo:rustc-link-lib,cargo:rustc-link-search,cargo:rustc-cfg,cargo:rustc-env, andcargo:warningdirectives. Done when:cargo buildreruns the script only when inputs change and the crate links or generates correctly. - Incremental builds and CI caching. If the task is CI caching, configure
Swatinem/rust-cache@v2oractions/cache@v3to cache~/.cargo/registryandtarget/. Set[profile.release] incremental = falsewhen release builds must stay deterministic. Done when: CI logs show cache hits and build times are stable. cargo nextest. If the task is test execution, installcargo-nextest 0.9.143and runcargo nextest run. Addnextest.tomlwith profiles for CI and local runs. Done when: tests pass under the chosen profile.- Dependency auditing. If the task is dependency auditing, run
cargo auditfromcargo-audit 0.22.2,cargo deny checkfromcargo-deny 0.20.2, orcargo machete. Configuredeny.tomlfor licenses, duplicate versions, and banned crates. Done when: the tool reports no blocking findings or names each finding. Cargo.lockmanagement. If the task is lock management, keepCargo.lockin version control for applications and binaries; omit it for libraries. Usecargo generate-lockfile,cargo update, andcargo update -p <crate> --precise <version>. Done when: the lock file matches the intended dependency versions.- Common commands. If the task is a one-off command, run the matching
cargo build,cargo test,cargo tree,cargo expand, orcargo packageinvocation for the requested crate and features. Done when: the command output confirms the requested state.
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.
- 3d ago First seen · 54 lines · 29 tokens per session scan A 9ebaf3fb48a8
cargo-workflows is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,283 once invoked, about $0.0001 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 2026-09-06.
Other skills, from other repositories
rust-crate-ci
Load before editing any Rust crate in this repo (currently runners/swarm-sandbox-runner). Covers the mandatory local validation gate, common rustfmt/clippy pitfalls, and Windows-specific Rust correctness patterns that CI enforces but are hard to catch locally without a Windows toolchain.
rust-tooling-cicd
Use when structuring a Cargo workspace or building a Rust CI pipeline — fmt, clippy, cargo-deny/audit, nextest, coverage, MSRV. Not for writing the tests themselves (rust-testing-quality).
cargo-workflows
Cargo workflow skill for Rust projects. Use when managing workspaces, feature flags, build scripts, cargo cache, incremental builds, dependency auditing, or CI configuration with Cargo. Activates on queries about cargo workspaces, Cargo.toml features, build.rs, cargo nextest, cargo deny, cargo check vs build, or…
rust-formal-verification
Use when Rust code, especially unsafe or panic-critical paths, needs a Kani, Verus, or Creusot harness written, run, and its failure read. Not for choosing the proof policy: use proof-driven.
libafl
Use when a LibAFL fuzzer needs an executor, observer, feedback, mutator, scheduler, or objective composed around a target. Not for remote, credential, publish, deploy, or irreversible changes.
scaffold-rust-cli
Scaffold a complete Rust CLI project with Cargo, cargo-deny, cargo-nextest, git-cliff, GitHub Actions CI/CD, and Makefile. Use when the user says "scaffold a Rust CLI", "new Rust CLI", "create a Rust binary crate", "start a Rust CLI", "bootstrap a Rust CLI", or starts a Rust command-line tool from scratch. Optionally…