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/code-reviewnpx skills add edimuj/tokenlean --skill code-reviewgit 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 | $0.00057 | $0.00653 |
| Opus 5 | $0.00028 | $0.00327 |
| Sonnet 5 | $0.00011 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
code-review 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review code changes thoroughly while reading as little raw code as possible.
Workflow
Changes → Scope check → Context gathering → Deep review → Output
1. Determine scope
# For a PR or branch
tl pr
# For uncommitted work
tl diff
# For a specific commit range
tl diff <ref>
If the diff is large (>20 files), focus on the highest-impact files first.
2. Gather context on changed files
For each changed file:
tl parallel \
"impact=tl impact <file>" \
"symbols=tl symbols <file>" \
"complexity=tl complexity <file>"
For files with high impact (many dependents), also run:
tl exports <file> # Was the public API changed? Are exports still compatible?
3. Review the code
Now read the actual diff. You already know:
- What changed (from step 1)
- What depends on it (from
tl impact) - The shape of the code (from
tl symbols) - Complexity hotspots (from
tl complexity)
Use tl snippet <function> <file> to read specific changed functions rather than full files.
4. Check for common issues
tl guard # Secrets, stale TODOs, unused exports, circular deps
5. Output format
Structure the review as:
## Summary
One-paragraph assessment: what this change does and overall quality.
## Issues
- **[severity]** file:line — description and suggestion
## Observations
- Non-blocking notes, style comments, questions for the author
## Verdict
APPROVE / REQUEST CHANGES / NEEDS DISCUSSION
Severity levels: critical (bugs, security), warning (potential problems), nit (style, minor).
Decision tree: how deep to go
File changed → How many dependents? (tl impact)
├─ 0 dependents → Light review (just read the diff)
├─ 1-5 dependents → Standard review (symbols + diff)
└─ 6+ dependents → Deep review (symbols + exports + snippet each changed function)
Tips
- Use
tl parallelto gather context on multiple changed files simultaneously - For test files, skip
tl impact(nothing depends on tests) tl symbols -jgives JSON output if you need structured data- If a file is under 150 lines, just read it directly — tokenlean overhead isn't worth it
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 · 100 lines · 57 tokens per session scan A a5cc94672a0a
code-review is a skill published in the GitHub repository edimuj/tokenlean (11 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 653 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.