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 akshayrao14/git-practices --skill dependabot-triagegit clone --depth 1 https://github.com/akshayrao14/git-practicesWrote 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/akshayrao14/git-practices/dependabot-triage)<a href="https://agentmods.dev/skills/akshayrao14/git-practices/dependabot-triage"><img src="https://agentmods.dev/badge/skills/akshayrao14/git-practices/dependabot-triage/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/akshayrao14/git-practices/dependabot-triage"><img src="https://agentmods.dev/badge/skills/akshayrao14/git-practices/dependabot-triage.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 | $0.00187 | $0.10682 |
| Opus 5 | $0.00093 | $0.05341 |
| Sonnet 5 | $0.00037 | $0.02136 |
| Haiku 4.5 | $0.00019 | $0.01068 |
Grade B, and why
dependabot-triage scanned grade B with 1 finding 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 9d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
Installs into the right skills dir for your agent (Codex `~/.codex/skills`, Claude Code `~/.claude/skills`, or open-standard `~/.agents/skills`). Restart your agent session afterward — the skill should appear in `/skills How it starts
The opening of the file, as written. The whole thing — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependabot Triage & Fix (v2.1)
v2.1 highlights
- Two modes — Standard and Fast-Track. Standard is the defensive workflow (full exposure mapping, changelog scrape, safety interlock). Fast-Track is for low-risk bumps (Internal/Dev category, CVSS < 7, or user opt-in) — skips changelog + detailed exposure enumeration, single-confirmation interlock. Parity check + dual-write are non-negotiable in BOTH modes.
- CI workflow inspection — first-class detection step. Lockfile alone doesn't tell you what runs in CI. CI may use a different PM than the committed lockfile (e.g. yarn.lock committed, CI runs
npm install), or may run<pm> installinstead of lockfile-strict<pm> ci. Detection drives the override + parity matrix. - Defensive versioning — pick the minimal patched version that fixes all in-cluster CVEs, not "latest in same major".
- Exposure Mapping replaces heuristic reachability — categorize every import site (Public/API · Client-Bundle · Internal/Dev) and present surface area to the user instead of trying to prove unreachability.
- Mandatory lockfile parity check — every PM that touches the manifest must resolve to the same version of the target package; mismatch aborts the PR. Required because CI/CD often runs a different PM than local sanity checks.
- Changelog scrape with safety interlock (Standard mode) — fetch release notes / CHANGELOG between current and target, flag
BREAKING/DEPRECATED/MIGRATIONkeywords, pause for explicit user confirmation before applying the bump. - Auto-reversion — if Fast-Track fails parity or the build fails post-bump, the skill offers to switch back to Standard mode for deeper analysis instead of grinding on retries.
- Org-level fan-out is opt-in only — never auto-trigger; org enumeration burns API rate limit and surfaces non-JS noise.
In scope for this skill: npm, pnpm, yarn (classic/berry), bun.
Scope
Only JavaScript / TypeScript repos — npm, pnpm, yarn, bun ecosystems. Covers backend Node.js services, frontend bundles (CSR), server-rendered apps (SSR), and mixed SSR+CSR frameworks (Next.js, Nuxt, Remix, SvelteKit).
What ships with it
4 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.
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.
- 9d ago First seen · 583 lines · 187 tokens per session scan B 4a1d556f585e
dependabot-triage is a skill published in the GitHub repository akshayrao14/git-practices (0 stars, last pushed 3d ago), licensed MIT. It adds 187 tokens to every session and 10,682 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
prisma-8
Comprehensive guide for building with Prisma 8 (Prisma Next), the contract-first data layer. Use whenever working on Prisma code in a project that uses it — authoring or editing the data contract (contract.prisma, PSL, TypeScript builders), migrations, queries (db.orm / db.sql), runtime wiring (db.ts, middleware…
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.
ax-event-runtime
Use AxEventRuntime to ingest events, explicitly wake or resume AxGen, AxAgent, and AxFlow, persist state and results, and route outputs safely.
credential-setup-with-computer-use
Guides n8n credential setup through Computer Use browser tools. Use when a user needs OAuth apps, API keys, client IDs, client secrets, or other credential values from an external service console.
output-dev-credentials
Store and reference encrypted secrets in Output SDK workflows using @outputai/credentials. Use when integrating API keys, database passwords, or third-party tokens.
walkeros-create-source
Use when creating a new walkerOS source to capture events (browser source, dataLayer interception, server/HTTP source, webhook receiver, event capture), web or server-side. Example-driven workflow: research the input format and define step examples before implementing the push interface, createTrigger, and env pattern.