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/githubnpx skills add edimuj/tokenlean --skill githubgit 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 | $0.00083 | $0.01332 |
| Opus 5 | $0.00042 | $0.00666 |
| Sonnet 5 | $0.00017 | $0.00266 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
github 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub & Git Operations
Token-efficient git and GitHub workflows via tl push, tl commit-prep, and tl gh.
Committing & Pushing
tl push
Stages, commits, and pushes in one call.
Critical: multi-file safety guard. When multiple files are modified and no explicit files are given, tl push refuses to proceed. It prints the modified file list and exits with code 1. You must specify which files to include.
# Single modified file — auto-stages
tl push "feat: add caching"
# Multiple modified files — MUST specify files
tl push "fix: resolve race" src/worker.mjs src/queue.mjs
# Include untracked (new) files
tl push "feat: new tool" bin/tl-new.mjs -A
# Commit without pushing
tl push "wip: checkpoint" src/foo.mjs --no-push
# Amend previous commit
tl push "fix: better msg" --amend
# Preview what would happen
tl push "test" --dry-run
tl commit-prep
Pre-commit context in one call: git status + diff stat + recent log. Use before tl push when you need to see what changed.
tl commit-prep
# then decide which files to include:
tl push "fix: typo" README.md
Workflow
Need to commit?
├─ Know which files → tl push "msg" file1 file2
├─ Need to see changes → tl commit-prep, then tl push "msg" file1 file2
└─ Only one file modified → tl push "msg" (auto-stages)
GitHub Operations — tl gh
Wraps multi-step GitHub API calls into single commands. Requires -R owner/repo.
When to use which tool
| Scenario | Tool |
|---|---|
| Single issue read with sub-issues or close with comment | tl gh issue read / tl gh issue close |
| Bulk operations (create/close/label many) | tl gh |
| View issue with direct sub-issues | tl gh issue read |
| Full PR status (CI + reviews + merge readiness) | tl gh pr digest |
| Check CI → merge → close issues → delete branch | tl gh pr land |
| Auto-generate release changelog | tl gh release notes |
Issue commands
# Read issue with sub-issues (single GraphQL call)
tl gh issue read -R owner/repo 434
tl gh issue read -R owner/repo 434 --no-body # compact
tl gh issue read -R owner/repo 434 --full # complete bodies
# Bulk create from JSON array or JSONL on stdin
echo '[{"title":"Bug A","labels":["bug"]},{"title":"Bug B"}]' | tl gh issue create-batch -R owner/repo
# Create parent + children with auto sub-issue links
cat tree.json | tl gh issue create-tree -R owner/repo
# Input: {"title": "Epic", "body": "...", "children": [{"title": "Task 1"}, {"title": "Task 2"}]}
# Link existing issues as sub-issues
tl gh issue add-sub -R owner/repo --parent 10 42 43 44
# Close one or more issues
tl gh issue close -R owner/repo 1 2 3 -c "Sprint complete"
tl gh issue close -R owner/repo 10 11 --reason "not planned"
# Add/remove labels in bulk
tl gh issue label-batch -R owner/repo --add "bug,P0" --remove "triage" 1 2 3
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 · 140 lines · 83 tokens per session scan A 9c2067e25bf8
github is a skill published in the GitHub repository edimuj/tokenlean (11 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,332 once invoked, about $0.0004 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.