tokenroom

tokenroom is a skill for Claude Code, Codex from tyejcoleman/tokenroom. It costs 74 tokens per session (4,348 once invoked), scanned A, original, Apache-2.0.

A skill for planning coding-agent work around two limits: account usage windows and the amount of conversation context available before summarization.

In plain words
What is it for?
Use it before large tasks or when budgets are low to size the work, save progress checkpoints, and choose when to continue or resume.
Why use it?
It helps decide when to split, defer, or checkpoint work so tasks fit within those limits and important context is preserved.

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/tyejcoleman/tokenroom/skill
Any agent
npx skills add tyejcoleman/tokenroom --skill skill
Clone the repo
git clone --depth 1 https://github.com/tyejcoleman/tokenroom

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tokenroom

README.md
[![agentmods](https://agentmods.dev/badge/skills/tyejcoleman/tokenroom/skill.svg)](https://agentmods.dev/skills/tyejcoleman/tokenroom/skill)
Your own site
<a href="https://agentmods.dev/skills/tyejcoleman/tokenroom/skill"><img src="https://agentmods.dev/badge/skills/tyejcoleman/tokenroom/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,348 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 $0.00074 $0.04348
Opus 5 $0.00037 $0.02174
Sonnet 5 $0.00015 $0.00870
Haiku 4.5 $0.00007 $0.00435

Measured 3d ago against content hash d6cea75e2d57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tokenroom 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 3d ago.

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.

skill/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tokenroom: plan within your budgets

You have two scarce budgets, and a [tokenroom] stamp reporting both arrives with user prompts when the tokenroom collector is installed:

  • Rate-limit windows (account-level): 5h: 34% left, resets 14:00 · 7d: 61% left. Subscription windows are use-it-or-lose-it; work attempted past exhaustion fails (429s) and in-flight work is wasted.
  • Context headroom (session-level): ctx: ~38k tokens before compaction. Past the ceiling the conversation is compacted and task continuity degrades.

All percentages in stamps and tools are remaining, never used.

How these budgets actually behave (do not conflate them)

  • Quota (the 5h/7d windows) is account-level spend. It refills ONLY at its reset clock. Low quota → defer heavy work past the reset (plan_resume).
  • Context is this session's working memory. No clock refills it — waiting does nothing. It changes only when compaction fires (automatic, near the ceiling) or the user runs /clear. Low context → save a checkpoint, then KEEP WORKING: compaction is automatic and survivable — tokenroom re-injects your checkpoint, repo ground truth, and pins immediately after it.
  • Never stop to "wait for context to come back at the reset" — that waits for the wrong resource and wastes wall-clock. If a fresh context window would genuinely help the next phase, ask the user to run /compact at a clean boundary; you cannot trigger it yourself.

Before any sizable task

  1. Estimate its cost. Rough priors: small localized fix ~3k tokens; medium task (docs pass, small feature) ~8–15k; large refactor or multi-file migration ~25k+.
  2. Call fit_check with that estimate (MCP tool, or trust the stamp if tools are unavailable). Act on the verdict:
Verdict Action
fits Proceed normally.
tight Proceed, but cheap-first, batch tool calls, no scope growth, land at a clean boundary.
exceeds (context) Do NOT start as-is: write a checkpoint/handoff first, or split so a piece fits.
defer (window) Do not start. Finish current work at a clean boundary, record a resume plan naming the reset time, and stop.

Read the full file on GitHub · 284 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. 3d ago First seen · 284 lines · 74 tokens per session scan A d6cea75e2d57

Subscribe to this mod's changes

tokenroom is a skill published in the GitHub repository tyejcoleman/tokenroom (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 4,348 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 2026-08-31.

Related

Other skills, from other repositories

tokf-filter

This skill should be used when the user asks to "create a filter", "write a tokf filter", "add a filter for ", "how do I filter output", or needs guidance on tokf filter step types, templates, pipes, or placement conventions.

mpecan/tokf · 59 tokens

accordion-context-recall

Read this skill when you need to read the full content of a folded context block RIGHT NOW as a tool result — without opening it in your standing context. Use recall(codes) when you only need a value once and do not want to permanently restore the block. Accordion may fold older parts of your context to keep token…

a-Fig/Accordion · 89 tokens

tokf-discover

Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.

mpecan/tokf · 24 tokens

clean-code

Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments.

diillson/chatcli · 21 tokens

yesresearch

Autonomous research loop — read plan, decompose, dispatch research agents, integrate, deliver wiki. For research tasks instead of coding. Runs as visible TUI agents in git worktree. Use when user says "yesresearch", "research ", "recherchiere ". Spawns cluster agents that use opencode built-in subagents (general…

carsteneu/yesmem · 87 tokens

janitor-value

Show whether each skill is earning its context-window cost — combined tokens-used view sorted by waste. Use when the user asks 'are my skills worth it', 'what's my context budget', 'which skills are dead weight', or wants to audit skill value, token cost, or usage. Trigger with '/janitor-value'.

khendzel/skills-janitor · 69 tokens