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 chadixearth/graphyloop --skill dependency-auditgit clone --depth 1 https://github.com/chadixearth/graphyloopWrote 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/chadixearth/graphyloop/dependency-audit)<a href="https://agentmods.dev/skills/chadixearth/graphyloop/dependency-audit"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/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/chadixearth/graphyloop/dependency-audit"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/dependency-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01407 |
| Opus 5.5 | $0.00030 | $0.00563 |
| Sonnet 5.5 | $0.00015 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00141 |
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 2mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency audit and supply chain
Two failures, opposite directions: shipping a package nobody vetted (install script, typosquatted name, unmaintained transitive dep), and burning a day on advisories that are unreachable in this app. Both come from not asking is this reachable, and what does it cost to remove.
When to activate
- Before
npm i <new-package>(or pip/go/cargo/composer equivalent). npm audit/ Dependabot / Snyk / GitHub alert, or a CI security job failing.- A PR whose diff includes a lockfile.
- Post-incident: "was this package the way in?"
Adding a dependency — the 60-second vet
- Do you need it? Platform first:
Intl,URL,fetch,crypto.subtle,structuredClone, CSS:has. A 3-line helper beats a transitive tree. - Is the name right? Typosquats live one character away
(
react-domm,lodash.js,crossenv,discord.js-selfbot). Copy the name from the official docs, never from a model's memory or a blog post. - Is it alive? Last publish, open-issue trend, maintainer count, downloads. One maintainer + last release three years ago = you are adopting the code.
- What does it drag in?
npm view <pkg> dependencies/npx howfat <pkg>— count transitives and installed size before, not after. - Does it run code on install?
npm view <pkg> scripts— apostinstallin a utility library is a red flag; install with--ignore-scriptsif you must. - License compatible? MIT/Apache-2.0/BSD fine for most products; AGPL/SSPL and "source-available" licenses are a legal decision, not a dev one.
- Pin it. Exact version in
package.json(no^for anything security- or build-critical), lockfile committed,npm ciin CI — nevernpm installthere.
Triaging an advisory
Run the tool, then think — the count is not the finding.
npm audit --json # or: pnpm audit / yarn npm audit
npm ls <vulnerable-pkg> # WHO pulls it in — the fix lives at that edge
pip-audit # python
govulncheck ./... # go: reports reachable symbols, not just versions
cargo audit # rust
composer audit # php
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.
- 2mo ago First seen · 110 lines · 74 tokens per session scan A 6ac0e5ad3ff2
dependency-audit is a skill published in the GitHub repository chadixearth/graphyloop (3 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,407 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
showrunner
Conduct a product from the owner's idea to release through one enforced lifecycle (setup, discovery, assessment, constitution, business documents, then per initiative intake, roadmap, spec, design, design review, handoff, Arc plan, Step 0, build, verify, security, acceptance, merge, release, close) using the Forge…
sentry
Sweep, triage, test, fix, verify, and maintain software security posture with categorical coverage, governed penetration testing, durable accepted-risk memory, refreshable standards knowledge, isolated fixes, and an unconditional stop before main. Use when initializing security bindings, reviewing application, mobile…
forge
Conceive products and features with an inventor without silently making product decisions. Use when initializing product bindings, discovering a product constitution from a raw idea, planning phases, writing a decision-complete feature specification, or appending an evidence-backed product decision before…
pen-test
Plan, execute, validate, retest, and report authorized penetration tests under Sentry with explicit rules of engagement, safety-classed actions, versioned test-case coverage, reproducible evidence, independent finding validation, and cleanup. Use when testing an owned or explicitly authorized web, API, mobile, cloud…
arc
Plan, dispatch, verify, and merge isolated software implementation arcs with maximum safe autonomy and an unconditional stop before main. Use when initializing repository build bindings, consuming an approved Forge specification or brief, rendering an implementer prompt, running a cold-context worker in an isolated…
bible
Synthesize the read-only architecture and capabilities document ("Bible") from the repository, the Forge spec, Arc ship reports, and Sentry security artifacts, binding every claim to a real path, interface, or named report and routing spec-promised but unbuilt capabilities to intent-not-shipped. Use when binding Bible…