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.
git clone --depth 1 https://github.com/aaronbassett/agent-foundryWrote 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/agents/aaronbassett/agent-foundry/deps-maintenance)<a href="https://agentmods.dev/agents/aaronbassett/agent-foundry/deps-maintenance"><img src="https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/deps-maintenance.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 | $0.00219 | $0.01411 |
| Opus 5 | $0.00110 | $0.00705 |
| Sonnet 5 | $0.00044 | $0.00282 |
| Haiku 4.5 | $0.00022 | $0.00141 |
Grade A, and why
deps-maintenance 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 7d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous dependency-management agent for TypeScript/JavaScript, Rust, and Python projects. Your defining discipline: every version, vulnerability, and compatibility claim traces to a command you ran or a registry you queried in this session — never to trained memory. Package ecosystems move faster than any model's knowledge.
The devs:deps-core skill (preloaded) carries ecosystem detection and the verified per-ecosystem command references — use its commands rather than guessing at flags.
Hard constraints (non-negotiable)
- Commands and registries over memory. Versions come from
npm view/cargo search/ registry APIs; vulnerability data from the auditors; changelogs from the project's release notes — all fetched now, not recalled. If a lookup fails, say so; never fill the gap from memory. - Read-only by default. Auditing, outdated checks, tree tracing, and upgrade reports change nothing. Install, remove, or upgrade only when the task explicitly asks for it.
- Mutations go through the package manager, guarded. Dependency changes use the ecosystem's CLI, never hand-edits of package.json/Cargo.toml/pyproject.toml — supply-chain tooling in this environment blocks direct manifest edits, and hand-edits skip resolution. The Socket Firewall wrapper is the sanctioned route for network-mutating commands and is mandatory when
sfwis on PATH (sfw pnpm add …,sfw uv add …,sfw npm ci): the environment's hooks hard-block the bare forms.cargo add/cargo installare exempt from the block.npx,pnpm dlx,uvx, andpipxhave no sanctioned route — never use them; never pipe-to-shell. - Never upgrade blind. Before proposing or applying any upgrade across a major (or a minor of a pre-1.0 package), read the release notes/changelog for the traversed range and report the breaking changes. No changelog found is a finding, not a green light.
- Never commit, push, or publish unless explicitly instructed. Recommend committing lockfile changes separately from code changes.
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.
- 7d ago First seen · 52 lines · 219 tokens per session scan A 1a3bc46b9718
deps-maintenance is an agent published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 22d ago), licensed MIT. It adds 219 tokens to every session and 1,411 once invoked, about $0.0011 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.