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 tahirraufkeeyu/software-development-agent-stack--sdas --skill dependency-auditgit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/dependency-audit)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/dependency-audit"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/dependency-audit.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 | $0.00074 | $0.01749 |
| Opus 5 | $0.00037 | $0.00874 |
| Sonnet 5 | $0.00015 | $0.00350 |
| Haiku 4.5 | $0.00007 | $0.00175 |
Grade A, and why
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 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger when:
- "Audit our dependencies" / "any CVEs in prod?" / "is log4shell present".
- Renovate / Dependabot fatigue — user wants a single prioritized list.
- Pre-release gate: block shipping on Critical CVEs in direct deps.
- Incident: a new CVE was just published, "are we vulnerable".
Do not use for SAST (use security-audit) or container layer CVEs (use
container-scan).
Inputs
REPO_PATH(default:.) — source tree to audit.OUT_DIR(default:./dep-audit-out).MIN_SEVERITY(default:MEDIUM) — filter floor.INCLUDE_DEV(default:0) — include dev-only deps.FAIL_ON(default:CRITICAL) — exit-code gate severity.- Optional env:
GITHUB_TOKEN— raises GitHub Advisory rate limits.OSV_API_URL— override osv.dev endpoint (for air-gapped).
Outputs
- Per-ecosystem raw:
osv.json,npm-audit.json,pip-audit.json,govulncheck.json,cargo-audit.json,dependency-check.json. dep-audit.normalized.json— unified records.dep-audit-report.md— grouped-by-severity report with fix table.
Unified record:
{
"ecosystem": "npm",
"package": "lodash",
"installed_version": "4.17.20",
"path": ["@my/app", "express-session", "lodash"],
"direct": false,
"cve": ["CVE-2021-23337"],
"ghsa": "GHSA-35jh-r3h4-6jhm",
"cvss": 7.2,
"severity": "high",
"summary": "Command Injection in lodash",
"fixed_in": "4.17.21",
"fix_kind": "patch",
"references": ["https://nvd.nist.gov/vuln/detail/CVE-2021-23337"]
}
Tool dependencies
osv-scanner>= 1.7 (universal, required).- Ecosystem tools (optional, each enables a manifest type):
npm/yarn/pnpmfor JS.pip-auditfor Python.govulncheckfor Go.cargo-auditfor Rust.- OWASP
dependency-checkfor Maven/Gradle.
jq.
Procedure
- Detect manifests. Presence rules:
package.json+ lockfile (package-lock.json,yarn.lock,pnpm-lock.yaml) -> JS.requirements.txt,pyproject.toml,Pipfile.lock-> Python.go.mod-> Go.Cargo.lock-> Rust.pom.xml,build.gradle*-> JVM.
- Run
../security-audit/scripts/run-sca.sh "$REPO_PATH" "$OUT_DIR"— it already knows how to dispatch per ecosystem. - Normalize each raw output into the unified schema. Key steps:
- OSV -> one record per
results[].packages[].vulnerabilities[]. - npm-audit v2 -> walk
vulnerabilitiesmap;direct: trueifvia[].dependency == <root>. - pip-audit ->
dependencies[].vulns[]. - govulncheck -> records where
finding.osv != nulland the trace reachesinternal/functions(callable, not just imported). - cargo-audit ->
vulnerabilities.list[].
- OSV -> one record per
- Build dependency path for each transitive finding using the lockfile
(
npm ls <pkg> --json,pip show,go mod graph,cargo tree -i <pkg>). Populatepathanddirect. - Compute CVSS: prefer NVD
cvssMetricV31.baseScore; fall back to GHSA severity string -> numeric midpoint (Low=2, Medium=5, High=8, Critical=9.5). - Filter below
$MIN_SEVERITY. - Produce
dep-audit-report.md:- Section per severity.
- Table columns:
Package | Installed | Fixed in | CVE | Severity | Direct/Transitive | Path. - "Fix plan" section with a concrete upgrade command per ecosystem
(e.g.
npm install [email protected],poetry add cryptography@^42.0.5,go get golang.org/x/[email protected]).
- Exit non-zero if any finding has severity >=
$FAIL_ON.
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 · 163 lines · 74 tokens per session scan A 3485f920c1c9
dependency-audit is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 1,749 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…