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/migrate-frameworknpx skills add edimuj/tokenlean --skill migrate-frameworkgit clone --depth 1 https://github.com/edimuj/tokenleanWhat 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 | $0.00058 | $0.00689 |
| Opus 5 | $0.00029 | $0.00345 |
| Sonnet 5 | $0.00012 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
migrate-framework 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate Framework
Migrate incrementally — never change more than one batch without running tests.
Workflow
Survey → Plan → Migrate → Verify → Clean up
1. Survey
Map the migration surface:
tl parallel \
"structure=tl structure" \
"search=tl search '<old-api-pattern>'" \
"stack=tl stack"
tl context7 <framework> "migration guide" -t 5000 # Official migration path
# Or: tl browse <migration-guide-url>
2. Plan
Group the work into safe increments:
tl parallel "impact=tl impact <file>" "related=tl related <file>"
Order: leaf files (0 dependents) first, shared utilities last. Each increment must leave the codebase in a working state.
3. Migrate
One batch at a time:
tl symbols <file> # Know the shape before modifying
tl snippet <function> <file> # Read each usage site
# Apply the migration pattern from the guide
tl diff --breaking # Catch accidental API changes after each batch
4. Verify
After every batch, not at the end:
tl parallel \
"test=tl run '<test command>'" \
"guard=tl guard" \
"exports=tl exports <file>"
# Commit after each passing batch
5. Clean up
Remove old-world artifacts:
tl parallel \
"search=tl search '<old-api-pattern>'" \
"unused=tl unused" \
"deps=tl deps <file>"
Decision tree
Migration request → How big is the surface?
├─ Small (<10 usages) → Single batch
│ → tl search to find all, migrate, tl run tests
├─ Medium (10-50 usages) → Batch by directory
│ → tl related to group files
│ → Migrate + test one directory at a time
│ → Commit after each batch
└─ Large (50+ usages) → Batch by dependency order
→ tl impact to sort files by dependents
→ Leaf files first, shared modules last
→ Migrate + test + commit per batch
→ tl search "<old-pattern>" to track remaining count
Tips
- Never start migrating without the migration guide — tl context7 or tl browse first
- Commit after each passing batch — if batch 7 breaks, you bisect to batch 7
- Use
tl search "<old-pattern>"to track how many usages remain after each batch - Leaf files first reduces risk — they have no dependents to break
- For large migrations,
tl impactoutput determines the safest execution order
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 First seen · 98 lines · 58 tokens per session scan A 2ef4ff925acf
migrate-framework is a skill published in the GitHub repository edimuj/tokenlean (11 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 689 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…
vs-search
Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.