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 agentmods add instructions/mattpicone/upgradelens/agents-mdgit clone --depth 1 https://github.com/mattpicone/upgradelensWrote 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/instructions/mattpicone/upgradelens/agents-md)<a href="https://agentmods.dev/instructions/mattpicone/upgradelens/agents-md"><img src="https://agentmods.dev/badge/instructions/mattpicone/upgradelens/agents-md.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 | $0.00648 | $0.00648 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
upgradelens AGENTS.md 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UpgradeLens v0.3 operating charter
UpgradeLens is a machine-only, read-only dependency-upgrade intelligence service for npm and PyPI. Its immutable machine contract is 0.3.1. The service never executes caller commands, clones repositories, follows caller-supplied URLs, or edits a caller's dependency files.
Current deployment is the existing Cloudflare Worker at
https://upgradelens.mattpicone.workers.dev (/mcp and /v1/*). Start local
work with npm ci; use npm run dev for a Worker preview or
npm run build for a Cloudflare bundle check.
Contract
check_dependency_upgrade: known current and target versions; returns a cited proceed/review/block/unknown decision.find_safe_upgrade_target: target unknown; returns ranked candidates only.plan_dependency_upgrade: target selected; returns ordered migration actions.- Every business result has
next_action,billing,decisionor candidates,action_allowed, freshness, coverage, and evidence near the top. - Errors use
{error:{code,message,retryable,details?}}. - The only supported ecosystems are npm and PyPI.
Access and payment
Health, discovery, schemas, pricing, initialize, and tools/list are free.
Each pseudonymous normalized-network identity receives one shared MCP/REST
business unit per rolling 30 days. A unit is exactly $0.01 / 10,000 atomic
USDC. Additional units use x402 v2; there are no subscriptions, prepaid
credits, checkout pages, API-key sales, or human approvals. Existing legacy
keys are compatibility identifiers only and never bypass payment.
Validation, testnet, mainnet, and paused are explicit payment modes. Mainnet must fail closed unless a verified recipient, facilitator credentials, recovery secret, release fingerprints, and matching testnet rollout attestation exist. Only a verified, settled, eligible Base-mainnet payment counts as revenue. Testnet, owner, duplicate, replayed, failed, refunded, or synthetic activity counts as zero revenue.
Operator workflow
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.
- yesterday Changed · +38 lines · +373 tokens per session f0533a8b5f0c
- 4d ago First seen · 20 lines · 275 tokens per session scan A ec60cea48df7
upgradelens AGENTS.md is an instructions file published in the GitHub repository mattpicone/upgradelens (0 stars, last pushed 4d ago), licensed MIT. It adds 648 tokens to every session, about $0.0032 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 instructions, from other repositories
dependency-fitness-mcp CLAUDE.md
Claude Code instructions for TweedBeetle/dependency-fitness-mcp, covering dependency-fitness-mcp — project memory, the product invariant (the moat — don't erode it), commands, layout and build gotchas (sdk 1.29 + zod v4).
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).