token-optimizer

A set of guidelines for reducing the amount of text an AI coding agent reads and writes during development work.

In plain words
What is it for?
Use it when running shell commands, inspecting code, testing, searching a codebase, or staging commits.
Why use it?
It helps avoid wasting tokens on long command output, full files, and unnecessarily broad test runs.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/phuonghx/aim-cli/token-optimizer
Any agent
npx skills add phuonghx/aim-cli --skill token-optimizer
Clone the repo
git clone --depth 1 https://github.com/phuonghx/aim-cli

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00579
Opus 5 $0.00022 $0.00290
Sonnet 5 $0.00009 $0.00116
Haiku 4.5 $0.00004 $0.00058

Measured yesterday against content hash 5945a61a179e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

token-optimizer 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.

aim/skills/token-optimizer/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Token Optimizer (aim-rtk)

AI agents pay for every token read or written. During development, excessive logs or full-file rewrites waste cost and exhaust context windows. Follow these optimization guidelines.

1. RTK (Rust Token Killer) Command Principles

Whenever running terminal commands, reduce output to the bare minimum needed for debug/analysis:

A. Git Operations (Save 60-80% tokens)

  • Status: Use git status -s instead of a raw git status.
  • Diff: Use git diff --stat first to see which files changed. Pull specific diffs via git diff <file> instead of dumping all files.
  • Log: Always limit history, e.g., git log -n 5 --oneline.
  • Commits: Avoid verbose outputs on pushes or pulls.

B. Builds & Compilation (Save 80-90% tokens)

  • Pipe command outputs to filter for errors or warnings (e.g. on Unix use cmd | grep -E "Error|Warning", on Windows use cmd | Select-String "Error").
  • For TypeScript, run tsc --noEmit but group outputs or check only modified files.
  • Avoid printing full successful build metrics.

C. Testing (Save 90-99% tokens)

  • Do not run the entire test suite in verbose mode.
  • Filter test runs to target only the specific file or test name:
    • Jest/Vitest: npm test -- -t "test-name"
    • Pytest: pytest -k "test_name"
    • Go: go test -run "TestName"
  • Instruct the runner to print failures only (e.g., --reporter=line or --summary-only).

D. File Navigation & Search (Save 60-75% tokens)

  • Do not read whole files just to locate a function or variable. Use grep search or symbol lookup first.
  • Only load line ranges of interest (e.g., lines 40-80) instead of reading 1000 lines.
  • Limit directory listing: use glob or git ls-files instead of listing all subdirectories recursively.

2. Token-Efficient Editing

  • Use targeted replacements: Never replace an entire file if you only need to modify a 10-line block. Use specific replace tools that replace precise lines by matching target content.
  • Commit frequently: Small commits keep the git diff concise, making it easier for subsequent AI steps to understand what changed.

Read the full file on GitHub · 42 lines

Changes

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.

  1. yesterday First seen · 42 lines · 43 tokens per session scan A 5945a61a179e

Subscribe to this mod's changes

token-optimizer is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 579 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

hs-release

Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.

vectorize-io/hindsight · 45 tokens

hindsight-local

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).

vectorize-io/hindsight · 32 tokens

research-repository

Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.

Owl-Listener/designer-skills · 43 tokens

design-negotiation

Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).

Owl-Listener/designer-skills · 48 tokens

user-persona

Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.

Owl-Listener/designer-skills · 50 tokens

version-control-strategy

Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).

Owl-Listener/designer-skills · 50 tokens