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 johnqtcg/awesome-skills --skill go-dependency-auditgit clone --depth 1 https://github.com/johnqtcg/awesome-skillsWrote 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/johnqtcg/awesome-skills/go-dependency-audit)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/go-dependency-audit"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/go-dependency-audit/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/johnqtcg/awesome-skills/go-dependency-audit"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/go-dependency-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 57 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 67 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00102 | $0.06944 |
| Opus 5.5 | $0.00041 | $0.02778 |
| Sonnet 5.5 | $0.00020 | $0.01389 |
| Haiku 4.5 | $0.00010 | $0.00694 |
Grade A, and why
go-dependency-audit 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 1mo 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 — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Reference
| When you need... | Jump to |
|---|---|
| Run a full dependency audit | S2 Gates -> S5 Checklist -> S9 Output |
| Scan for known CVEs | S2 Gates -> S5.1 CVE Scanning |
| Triage a finding / decide urgency | S6 — evidence tier, NOT a CVSS guess |
| Check license risk | S5.2 + references/license-compliance.md |
| Plan a version upgrade | S5.3 + references/upgrade-planning.md |
| Investigate supply chain risk | S5.4 + references/supply-chain-security.md |
| Review go.mod hygiene | S5.5 Module Hygiene |
| Actually apply a fix | S1.3 Remediation Boundary |
1 Scope & Operating Mode
1.1 In scope
go.mod/go.sum analysis, CVE scanning via govulncheck (primary), license risk
triage, outdated dependency reporting, upgrade path planning, breaking change
assessment, supply chain posture (proxy, checksum DB, private modules),
+incompatible triage, module graph analysis.
1.2 Out of scope
Application code security (use security-review), micro-benchmark performance
(use go-benchmark), infrastructure provisioning, container image scanning,
runtime behavior analysis, and legal determinations about license
obligations — see S5.2: this skill produces evidence and escalation triggers,
never verdicts.
1.3 Remediation Boundary (NON-NEGOTIABLE)
An audit is read-only. It observes; it does not repair.
| Class | Commands | Allowed during audit |
|---|---|---|
| Read-only probe | govulncheck, go list -mod=readonly, go mod graph/verify/why, go mod edit -json, go mod tidy -diff, go version -m, go env <VAR>…, go-licenses check/report/help, git status/diff/log |
Yes |
| Mutating | go get, go mod tidy (without -diff), go mod edit -require, go work, go env -w, go list -mod=mod, go-licenses save, go install, cyclonedx-gomod -output |
No — emit as plan |
| Destructive | git checkout, git restore, git reset, rm |
Never — not even to roll back |
What ships with it
48 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.
- references/anti-examples.md 4.1 KB
- references/govulncheck-patterns.md 17 KB
- references/license-compliance.md 14 KB
- references/multi-module.md 8.7 KB
- references/scorecard.md 4.3 KB
- references/supply-chain-security.md 17 KB
- references/upgrade-planning.md 15 KB
- scripts/eval_forward.py 38 KB runs code
- scripts/lint_dep_audit_docs.py 34 KB runs code
- scripts/run_regression.sh 1.6 KB runs code
- scripts/tests/COVERAGE.md 13 KB
- scripts/tests/eval/DA-E1.json 889 B
- scripts/tests/eval/DA-E2.json 726 B
- scripts/tests/eval/DA-E3.json 660 B
- scripts/tests/eval/DA-E4.json 758 B
- scripts/tests/eval/DA-E5.json 670 B
- scripts/tests/eval/DA-E6.json 798 B
- scripts/tests/fixtures/govulncheck/clean.json 310 B
- scripts/tests/fixtures/govulncheck/mixed_tiers.json 2.0 KB
- scripts/tests/fixtures/govulncheck/module_scan_only.json 1.2 KB
- scripts/tests/fixtures/govulncheck/real_scan_x_net_v0.15.0.json 28 KB
- scripts/tests/golden/001_reachable_symbol_finding.json 1.2 KB
- scripts/tests/golden/002_no_scan_claiming_safety.json 908 B
- scripts/tests/golden/003_gosum_integrity_failure.json 993 B
- scripts/tests/golden/004_module_tier_reported_as_reachable.json 1.1 KB
- scripts/tests/golden/005_license_legal_verdict.json 1.1 KB
- scripts/tests/golden/006_incompatible_version.json 1.1 KB
- scripts/tests/golden/007_go_get_u_danger.json 965 B
- scripts/tests/golden/008_fabricated_cvss.json 1012 B
- scripts/tests/golden/009_destructive_rollback.json 1.1 KB
- scripts/tests/golden/010_json_gate_cannot_fail.json 862 B
- scripts/tests/golden/011_module_cycle_as_failure.json 916 B
- scripts/tests/golden/012_good_clean_audit.json 1.1 KB
- scripts/tests/golden/013_good_targeted_upgrade.json 1.0 KB
- scripts/tests/golden/014_degraded_no_gomod.json 718 B
- scripts/tests/golden/015_degraded_no_govulncheck.json 873 B
- scripts/tests/golden/016_workflow_full_audit.json 971 B
- scripts/tests/golden/017_workflow_supply_chain.json 999 B
- scripts/tests/golden/018_quick_mode_scope.json 834 B
- scripts/tests/golden/019_anti_example_lookup.json 948 B
- scripts/tests/golden/020_monorepo_single_module.json 1.1 KB
- scripts/tests/golden/021_degraded_audit_scored_pass.json 923 B
- scripts/tests/golden/022_cross_module_aggregation.json 1.4 KB
- scripts/tests/test_doc_lint.py 17 KB runs code
- scripts/tests/test_forward_eval.py 20 KB runs code
- scripts/tests/test_golden_scenarios.py 11 KB runs code
- scripts/tests/test_govulncheck_recipes.py 30 KB runs code
- scripts/tests/test_skill_contract.py 22 KB runs code
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.
- 1mo ago First seen · 473 lines · 102 tokens per session scan A a3f14f355b1f
go-dependency-audit is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed 17d ago), licensed MIT. It adds 102 tokens to every session and 6,944 once invoked, about $0.0004 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.
Other skills, from other repositories
agent-go-expert
Specialist subagent: Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
golang-rules
Go coding rules: style, patterns, security, testing. Triggers: .go, go.mod, go.sum, Gin, Echo, Gorilla, testing, gofmt.
go-concurrency-guide
Développement Go avec focus sur la concurrence et les patterns idiomatiques. Se déclenche avec "Go", "Golang", "goroutine", "channel", "sync", "concurrency", "Go modules", "Go patterns", "interface Go". Also triggers on "Go goroutines", "channels in Go", "Go concurrency pattern".
aio-golang-mastery
Write, review, and lint Go code. Lint mode runs go build, go vet, golangci-lint, govulncheck, nilaway, deadcode, and race detection (race detector), then applies idiomatic fixes. Reference mode covers concurrency, error handling, generics, testing, gRPC, and production hardening. Use when asked to lint golang, run a…
copilot-sdk
Build applications powered by GitHub Copilot using the Copilot SDK — session management, custom tools, streaming, hooks, MCP servers, BYOK, deployment patterns.
go-linter-configuration
Configure and troubleshoot golangci-lint for Go projects. Includes complete .golangci.yml examples, import resolution fixes, CI optimization, and linter selection workflows.