Audit Go Project Agent Skill

Audit a Go project's dependencies for known vulnerabilities, unmaintained modules, and unused requirements.

Context cost
975 tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 3.9 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Audit a Go project's dependencies for known vulnerabilities, unmaintained modules, and unused requirements. Use when asked to security-scan, vuln-check, dependency-audit, or health-check a Go module and its dependency tree. Relies on the pkgsite MCP tools (get_vulnerabilities, get_module, list_module_versions).

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

securitytesting

The skill itself

A skill is instructions the model reads, and here they are in full: the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md3.9 kB
--- name: audit-go-project ---
6Audit the Go project (the path the user gives, or the current directory) and all of its dependencies — including test-only dependencies, which run on CI — for security and maintenance risk. Run local Go commands from that project directory. The pkgsite MCP tools (get_vulnerabilities, get_module, list_module_versions) are the primary source; govulncheck, when available, is an additional reachability check, not the main scanner.
7
81. Enumerate the modules and their selected versions with go list -m all (it covers build and test dependencies); if no Go toolchain is available, read go.mod and go.sum from the project directory. Also run go list -deps -test ./... there to learn which modules are actually imported (by build or test code) versus only present in the graph.
92. Known vulnerabilities: for each module at its selected version, call get_vulnerabilities to list advisories from the Go vulnerability database. A "not found" (404) means that version could not be checked — common for pseudo-versions (untagged v0.0.0-<commit>) — so treat it as unknown, not clean. For each advisory, find the fixed version; if get_vulnerabilities omits it, call list_module_versions and re-check newer versions for the first clean one, skipping any version it marks retracted. Additionally, if govulncheck is available, run govulncheck -test ./... from the project directory to see which advisories are reachable from the code or tests (-test covers test code and test-only deps; if it fails to load because the tests do not compile, retry without -test and say so). Use its reachability as extra signal on top of the pkgsite results, not as a replacement.
103. Unmaintained modules: call get_module for each module to read its latest version and commit time, and list_module_versions for its release history, the per-version retracted flag, and the module-wide deprecated flag (declared by the latest version's go.mod). Flag modules whose latest release is old (roughly two years or more) or several releases behind the version in use. Report an author-deprecated module prominently — it is the clearest "no longer supported" signal — and treat using a retracted version as a defect to fix regardless of age. go list -m -u all also lists available updates and deprecated modules, but list_module_versions gives the same signal without a toolchain.
114. Unused modules: prefer go mod tidy -diff from the project directory — the require entries it would remove are the genuinely unused ones, since it keeps modules still needed transitively. If that is unavailable, approximate by flagging modules in the graph that no package imports, but note that over-reports legitimate transitive dependencies. Recommend go mod tidy to drop the unused requirements.
12
13Then report, in this order:
14- A one-line summary, e.g. "Scanned 40 modules: 2 vulnerable, 3 unmaintained, 5 unused."
15- Vulnerabilities: a table of only the affected modules (module, version, advisory ID, summary, fixed version, and — if govulncheck ran — whether the code or tests reach it). Skip if none.
16- Unmaintained: a short table (module, version, latest, latest release date, reason: retracted / deprecated / stale / behind). Skip if none.
17- Unused: a list of modules removable with go mod tidy. Skip if none.
18- The minimal upgrades and removals you recommend, prioritizing reachable vulnerabilities.
19
20If govulncheck was not available, note that vulnerability results reflect advisories by module and version only, not reachability, and do not cover the Go standard library or toolchain.
21
This is the whole of SKILL.md. Install the skill to get it and everything beside it.
In the file
SKILL.md597 words
Files1
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈90
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
885
on trigger
The instruction body, read only when the skill fires.
0.49%
of a 200k window
Ten skills this size would take about 5% of the window before you open a file.
050k100k150k200k context window

975 tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Small enough to keep loaded permanently without thinking about it.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md, shown in full above.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 3.9 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md3.9 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Audit Go Project · 975 tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/audit-go-project/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/audit-go-project" ] && { [ ! -e .claude/skills/audit-go-project ] || { mv .claude/skills/audit-go-project "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/audit-go-project" .claude/skills/ && echo "Installed .claude/skills/audit-go-project"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add sv-tools/audit-go-project

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/audit-go-project/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/audit-go-project/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/audit-go-project" ] && { [ ! -e ~/.claude/skills/audit-go-project ] || { mv ~/.claude/skills/audit-go-project "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/audit-go-project" ~/.claude/skills/ && echo "Installed ~/.claude/skills/audit-go-project" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/audit-go-project/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencesv-tools/audit-go-project

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

ST
sv-tools

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill