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/explore-codebasenpx skills add edimuj/tokenlean --skill explore-codebasegit 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 | $0.00060 | $0.00636 |
| Opus 5 | $0.00030 | $0.00318 |
| Sonnet 5 | $0.00012 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
explore-codebase 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore Codebase
Understand a project in minutes by reading as little raw code as possible.
Workflow
Structure → Key areas → Drill down → Report
1. Get the map
tl structure
This shows directories, file counts, and token estimates. Identify:
- Where the bulk of the code lives
- Entry points (usually obvious from directory names)
- Test coverage presence
2. Find entry points and hot files
tl parallel "tl entry" "tl hotspots"
Entry points tell you where execution starts. Hotspots tell you where development is active.
3. Understand key files
For each important file identified above:
File size → Decision
├─ <150 lines → Just read it
├─ 150-400 lines → tl symbols first, tl snippet for specifics
└─ 400+ lines → tl symbols only, then tl snippet as needed
# Per file, gather context in one call:
tl parallel "symbols=tl symbols <file>" "deps=tl deps <file>" "exports=tl exports <file>"
# Or for entire directories:
tl symbols src/ # All files in a directory (compact one-liner per file)
tl symbols a.ts b.ts # Multiple specific files (compact)
4. Trace the dependency graph
Pick the most central file (usually has the most importers):
tl parallel "impact=tl impact <file>" "flow=tl flow <function> <file>"
This reveals the architecture: which modules are core infrastructure vs. leaf nodes.
5. Check conventions
tl style # Coding conventions (naming, formatting, patterns)
Run once at the start of a session to match the project's style.
6. Report
Summarize your understanding:
## Project overview
What it does, in one sentence.
## Architecture
Key directories and their roles. How data/control flows.
## Key files
The 5-10 most important files with one-line descriptions.
## Patterns
Conventions, frameworks, notable architectural decisions.
## Entry points
Where execution starts, how to run/test.
Tips
- Use
tl parallelto gather context on multiple files simultaneously tl context <dir>shows token cost of a directory — skip reading dirs over 50k tokens directly- For React/frontend projects, also run
tl componenton main UI files - For API projects,
tl apiandtl routesreveal endpoint structure
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 · 101 lines · 60 tokens per session scan A 09ae61a6efec
explore-codebase is a skill published in the GitHub repository edimuj/tokenlean (11 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 636 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.