agentleFS
tanishq286tanishq286/tq-forge/skills/savings/SKILL.md

savings

Skill8 starsChanged 5 months agoMITView on GitHub

Show how many tokens and dollars each tq-forge mod has saved. Use when asked for "/savings", "what did the mods save", "token savings", or "is the input router worth it".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a mod shows zero events, say it has not fired yet.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/savings

When to use

Run this when the user wants to see what the tq-forge mods have done so far: tokens kept out of the conversation by the input router and the screenshot shrinker, subagent runs that were routed to a cheaper model, effort recommendations, and warm versus cold cache turns. It reads one local file and changes nothing.

Procedure

  1. Print the dashboard:
M="$HOME/.claude/hooks/tq-forge/mods.py"; [ -f "$M" ] || M=".claude/hooks/tq-forge/mods.py"
python3 "$M" savings
  1. Show the table to the user as it is. Do not round the numbers or add rows.
  2. Say which figures are estimates: tokens are characters divided by four, image tokens are pixels divided by 750, and dollars use list prices.
  3. If a mod shows zero events, say it has not fired yet. That is different from saving nothing.

Pitfalls

  • The Effort Optimizer row counts recommendations. A hook cannot change effort, so it saves tokens only when the user follows one.
  • The Context Optimizer row is what optimize --apply runs took off every turn. It is a per-turn figure, not a running total, so it is left out of the Total line. restore does not reset it.
  • The Input Router figure for a routed file assumes the file was handed to the reader subagent. If it was read in ranges instead, the real saving is smaller.

Verification

  • The command exits 0 and prints seven rows plus a total.
  • The raw data is in ~/.claude/tq-forge-savings.json if the user wants to check an event.

Tags

savings, tokens, mods, dashboard

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.