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/safe-refactornpx skills add edimuj/tokenlean --skill safe-refactorgit 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 | $0.00054 | $0.00640 |
| Opus 5 | $0.00027 | $0.00320 |
| Sonnet 5 | $0.00011 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
safe-refactor 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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Refactor
Change code structure without breaking dependents.
Workflow
Analyze → Plan → Change → Verify
1. Analyze what you're changing
tl parallel \
"impact=tl impact <file>" \
"exports=tl exports <file>" \
"symbols=tl symbols <file>"
These three commands tell you:
- Blast radius — how many files will be affected
- Contract — which exports are consumed externally
- Shape — what you're working with
If tl impact shows 10+ dependents, consider whether this refactor is worth the risk. Discuss with the user.
2. Understand consumers
For each file that imports from the target:
tl snippet <imported-symbol> <consumer-file>
This shows how the symbol is actually used without reading the entire consumer file.
3. Make the changes
Apply the refactor. Then immediately check:
tl guard # Circular deps, unused exports, other issues
4. Verify
tl parallel "test=tl run '<test-command>'" "impact=tl impact <file>"
If tests fail, tl run output shows only the failures. Fix and re-run.
Decision tree: refactor type
What are you changing?
├─ Renaming a symbol
│ → tl impact to find all importers
│ → Update all import sites
│ → tl guard to verify no broken imports
│
├─ Moving a file
│ → tl impact for full dependent list
│ → Move file, update all import paths
│ → tl guard for circular deps
│
├─ Extracting a function/module
│ → tl symbols + tl deps on source file
│ → Extract, add exports
│ → tl impact on original to update importers
│ → tl guard + tl run tests
│
└─ Changing a function signature
→ tl impact + tl flow to find all callers
→ tl snippet on each caller to see usage
→ Update signature + all call sites
→ tl run tests
Tips
- Always check tl impact BEFORE starting — discovering 50 dependents mid-refactor is painful
- Run tl exports before and after: the diff shows if you accidentally changed the public API
- For large refactors (10+ files), make incremental commits so you can bisect failures
tl unusedafter refactoring catches exports you forgot to clean up
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.
- 2d ago First seen · 92 lines · 54 tokens per session scan A 3fc97a460ae9
safe-refactor is a skill published in the GitHub repository edimuj/tokenlean (11 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 640 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.