Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sbom-tool/gh-guardnpx agentmods add skills/sbom-tool/gh-guard/workspace-publishingWrote 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/sbom-tool/gh-guard/workspace-publishing)<a href="https://agentmods.dev/skills/sbom-tool/gh-guard/workspace-publishing"><img src="https://agentmods.dev/badge/skills/sbom-tool/gh-guard/workspace-publishing.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.01876 |
| Opus 5 | $0.00009 | $0.00938 |
| Sonnet 5 | $0.00004 | $0.00375 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
workspace-publishing 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 8d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Publishing for Rust
Multi-crate Rust workspaces require careful publish ordering, per-crate Trusted Publishing configuration, and coordinated version bumps. This skill covers the patterns and gotchas for publishing workspace projects.
Scope
This skill covers Cargo workspaces — projects with [workspace] in root Cargo.toml where members share a Cargo.lock and can have inter-crate dependencies.
Not covered: Monorepos with multiple independent Cargo.toml files that are NOT connected by [workspace]. For those, treat each crate as an independent project and apply the standard (non-workspace) patterns from other gh-guard skills. Each crate gets its own CI, publish workflow, and Trusted Publishing config.
Detecting Workspace Projects
A workspace is identified by [workspace] in the root Cargo.toml:
[workspace]
members = ["core", "parser", "cli"]
Use cargo metadata to list publishable members:
cargo metadata --no-deps --format-version 1 \
| jq -r '.packages[] | select(.publish == null or (.publish | length == 0) or (.publish | index("false") | not)) | .name'
Crates with publish = false in their Cargo.toml are not publishable and should be excluded from the publish workflow.
Publish Ordering
Workspace crates must be published in dependency order — a crate's dependencies must be available on crates.io before it can be published.
Determining Order
Use cargo metadata to build the dependency graph:
cargo metadata --no-deps --format-version 1 \
| jq -r '.packages[] | "\(.name): \([.dependencies[] | select(.path != null) | .name] | join(", "))"'
Example output and ordering:
core: (no local deps) → publish first
parser: core → publish second
cli: core, parser → publish third
Index Propagation Delay
After publishing a crate, crates.io needs ~60 seconds to index it before dependents can find it. The publish workflow must include a sleep between crates:
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.
- 8d ago First seen · 212 lines · 18 tokens per session scan A 83c2ba9365c2
workspace-publishing is a skill published in the GitHub repository sbom-tool/gh-guard (15 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 1,876 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 2026-08-30.
Other skills, from other repositories
release
Evaluate readiness and publish to crates.io.
update-v8-version
Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.
cargo-release
PM-invocable protocol for Cargo publish and release operations in the trusty-tools Rust monorepo: semver rules, 10-step release sequence, macOS codesign safety, and cross-crate dependency ordering.
rust-release
Plan and execute Rust release engineering. Use when: publishing a crate, setting up release automation, cross-compiling binaries. Do not use: for version bumping alone, local build setup.
cargo-publish
Operate the socket-release crates.io flow - the cargo staged model (dry-run default), trusted publishing via OIDC under the cargo-publish environment, index-propagation waits, and yank-as-rollback. Use when publishing a Rust crate in a repo carrying scripts/socket-release/.
jackin-release
Use only when the user explicitly requests this skill. Cuts a jackin❯ release — runs the readiness gates, writes the changelog, recommends a version, then executes cargo release on explicit operator confirmation.