Token Consumer — Development skill for Claude Code
Measure and shrink the token cost of Claude Code skills, tier by tier: the always-on system-prompt tax, the per-invocation body, and on-demand references, each priced at the rate it is actually billed.
How to install Token Consumer
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Shult/token_consumer and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Token Consumer does
Measure and shrink the token cost of Claude Code skills, tier by tier: the always-on system-prompt tax, the per-invocation body, and on-demand references, each priced at the rate it is actually billed.
Alternatives in Development
- Arrecall — AgentRecall on-demand recall — surface past fixes, decisions, and patterns mid-session without leaving your fl 370 ★
- Check Setup.En — Top-level alias — see lesson/check-setup.en.md for the full body 347 ★
- Gov Backlinks — Free .gov backlinks - drive the user's browser through SAM.gov, the SBA small business listing, and state vend 195 ★
README
tokc — token consumption analyzer for Claude Code skills
[](https://github.com/Shult/token_consumer/actions/workflows/ci.yml) [](https://pypi.org/project/tokc/) [](https://pypi.org/project/tokc/) [](LICENSE)
Measures what a skill actually costs you, tier by tier, and tells you where to cut.
29 skill(s) tokenizer: o200k_base x1.180 (default)
SKILL T1/sess T2/use T3 ALWAYS-ON TAX $/mo
------------------------------------------------------------------------------
project-artifact 241 5,415 8.5k ████████████████████████ ! $2.99
receipts 159 4,865 20k ████████████████ ! $2.40
hook-development 140 4,548 16k ██████████████ $2.20
...
------------------------------------------------------------------------------
TOTAL 2,787 99,352 294k $45.65
Always-on tax
2,787 tokens ride in the system prompt of every request, in every session,
whether or not any skill fires.
-> 2.9M billed token-equivalents/month at 200 sessions x 40 requests
Listing budget (characters, not tokens)
████████████████████████████████████████ 10,577 / 8,000 chars (132%)
window 200,000 tokens x 4 chars/token -- model `sonnet`, ~/.claude/settings.json
! 2,577 chars over budget -- 6 skill(s) ship as `- name`, description omitted
demoted, least-used first: plugin-structure, project-artifact, receipts, ...
Why this exists
Existing tools estimate skill cost by asking Claude — which costs tokens and gives different numbers each run — or by running `tiktoken` over `SKILL.md`, which **undercounts Claude by 15-20%*
Related Skills
Skill Compact
Shrink Claude Code SKILL.md token cost without breaking skills. Trigger-preserving description gate + lossless
Downside Case
Builds the strongest possible case for NOT building a feature. Acts as a rigorous adversary, evaluating opport
Codex Consult
Consult OpenAI Codex (codex exec) for a second opinion on a prompt. Handles the argv-hang, stdin-mode, reasoni
Problem Solver Skill
Claude Code skill for systematic problem diagnosis using progressive disclosure — 55-line router + 7 on-demand
Hatch3r Create
Author a custom user-tier artifact (agent, skill, rule, command, or hook) for this project. Generates frontmat
Glm Subagent MCP
Delegate work to a Claude Code subprocess billed against a GLM Coding Plan.
Related Agents
Selfish Reputation
Measure whether the body of work is increasing qualified trust, recognition, referrals, repeat engagement, and
Legal Compliance Uk
Use to flag UK legal, tax, and regulatory exposure — company structure, VAT, GDPR/PECR, consumer law, sector r
Authz Auditor
Phase 6 authorization and access-control audit agent that enumerates every route/handler/consumer across the c