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 skills/edimuj/tokenlean/upgrade-depsnpx skills add edimuj/tokenlean --skill upgrade-depsgit clone --depth 1 https://github.com/edimuj/tokenleanWrote 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/edimuj/tokenlean/upgrade-deps)<a href="https://agentmods.dev/skills/edimuj/tokenlean/upgrade-deps"><img src="https://agentmods.dev/badge/skills/edimuj/tokenlean/upgrade-deps.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 | $0.00053 | $0.00601 |
| Opus 5 | $0.00026 | $0.00300 |
| Sonnet 5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
upgrade-deps 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 4d 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.
What it actually says
Upgrade Deps
Upgrade dependencies safely by understanding usage before changing versions.
Workflow
Audit → Research → Upgrade → Verify → Clean up
1. Audit
Understand current usage before changing anything:
tl parallel \
"npm=tl npm <package>" \
"search=tl search '<package-name>'" \
"deps=tl deps <file>"
2. Research
Check what changed between versions:
tl parallel "browse=tl browse <changelog-url>" "docs=tl context7 <package> 'migration guide'"
Look for: removed APIs, renamed functions, changed defaults, new peer deps.
3. Upgrade
Apply the version bump:
# Update package.json and install
tl diff --breaking # Detect signature mismatches in wrapper files
tl snippet <symbol> <file> # Check each usage site against new API
4. Verify
tl parallel \
"test=tl run '<test command>'" \
"testmap=tl test-map <file>" \
"guard=tl guard"
5. Clean up
Remove old compatibility code:
tl parallel "unused=tl unused" "search=tl search '<old-version>'"
Decision tree
Upgrade request → How big is the version jump?
├─ Patch (1.2.3 → 1.2.4) → Light check
│ → tl npm to confirm, upgrade, tl run tests
├─ Minor (1.2 → 1.3) → Standard check
│ → tl search for usage, tl browse changelog
│ → Upgrade, tl run tests
└─ Major (1.x → 2.x) → Full audit
→ tl search for all usage sites
→ tl browse changelog + migration guide
→ tl snippet on every consumer
→ Upgrade, tl diff --breaking, tl run tests
→ tl unused to clean up compat code
Tips
- tl npm output includes the changelog URL — use it with tl browse
- Use tl context7 for popular frameworks (React, Next.js, etc.) — it has migration guides
- Always check for changed peer dependencies after major upgrades
- Run tl unused after removing compatibility code — catch leftover dead exports
- Never upgrade a major version without reading the migration guide first
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.
- 4d ago First seen · 89 lines · 53 tokens per session scan A c51fa7c94478
upgrade-deps is a skill published in the GitHub repository edimuj/tokenlean (11 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 601 once invoked, about $0.0003 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
zerodust
Sweep 100% of native gas tokens (ETH, BNB, MATIC, etc.) from EVM chains via ZeroDust, leaving exactly zero balance. Use when: user wants to exit a chain completely, consolidate dust balances, clean up wallets, or bridge remaining native tokens cross-chain. Supports 25 mainnet chains including Ethereum, Base, Arbitrum…
ctx2img
Cut context tokens by rendering it as images. ctx2img paint turns any text-shaped input (a repo, a directory, a file, markdown, stdin) into dense images that carry the full text at 60-75% fewer tokens, with stable handles and a verbatim factsheet; ctx2img read recovers guaranteed-exact text. Use before ingesting any…
r3f-animation
React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
muapi-ui-design
Generate high-fidelity UI/UX mockups for mobile and web apps using Atomic Design principles — creates wireframes and design systems via muapi.ai.