Abo Flesابو فليس
NEW 2.13.0 Prompt checkup: vague agent briefs get sent back

Your agents spend like it's a wedding.

Abo Fles is a free plugin for Claude Code that picks the model and effort for every subagent. Haiku reads, Sonnet checks, Opus builds — and you get the receipt.

/plugin marketplace add Sajadh92/abofles
Free & MIT30 versions since Oct 2026No account, no data sent
The real Abo Fles pane in the Claude desktop app: Home page with Next up, Context 152K of 500K, a task list at step 2 of 7, and Agents 24% saved.
The problem

Every subagent inherits your most expensive setting.

Run your main session on Opus · High and every agent it starts does too — the one that writes your payment code, and the one that just looks for a file. The uncle sorts them.

Without the uncle
Where is login called?Opus · High
Fix refund roundingOpus · High
Instagram reel captionOpus · High

Same price for a grep and a ledger change. No reviewer on the money. No receipt, so nobody knows.

With Abo Fles
🟢 Where is login called?Haiku · Low
🔴 Fix refund roundingOpus · Extra + 3 reviewers
🟢 Instagram reel captionOpus · Low

Cheap where a mistake is cheap, careful where it costs money. The same 1M-token read: $0.03 on Haiku 5.5, $0.90 on Opus 5.5.

Who it's for

Devs, designers, marketers. One uncle.

1,317 topics in 31 domains — from SQL migrations to TikTok ads. Each one knows how risky it is and who should check it. These are real lookups.

Money code gets the whole family. A grep gets Haiku.

  • Payments, auth, secrets and data loss route to 🔴 Critical: plan, work and verify on the strongest settings.
  • Finance, Security and Tester review the change after Verify passes, in parallel.
  • Reading questions — “where is X”, “what calls Y” — stay on Haiku · Low, even in money code.
  • A Git agent owns every commit and push. Force pushes need your words.
How it works

You ask. He haggles. The work gets done.

You ask, like always

No new commands to learn. Type the task in Claude Code the way you already do.

He looks it up

One lookup finds the topic and its risk tier — 🟢 Minor to 🔴 Critical — and picks a model, effort and reply cap for each step: Read, Analyse, Plan, Work, Verify.

Agents run, you get the receipt

Hooks refuse any agent without a model and effort. At the end: agents, real tokens, real dollars, and what was saved.

Features

Everything a stingy uncle would build.

Strict about money, generous with checks. All of it on by default, all of it one line to change.

Model router

Every subagent gets a model and effort from a topic × side matrix. Opus writes, plans and analyses; Haiku and Sonnet read and verify. Fable only thinks.

“Opus to grep? Habibi, no.”

1,317 topics, 4 tiers

31 domains for code, design and marketing, each topic tiered by what a mistake costs. A one-call lookup — the model never reads the list.

Knows a little about everything. Like every uncle.

Receipts

Every task that started agents ends with one: agents, real tokens, real dollars and the saving versus your main model. /abofles:bill for the whole session.

He asks for the receipt. Every. Single. Time.

Agent gate

Asks once per session how many agents a task may start, sized by tier. Caps background agents, so a session never runs ten without you knowing.

“Ten agents at once? Who's paying for this wedding?”

Judge before questions

No question reaches you before a Judge tried to answer it from the code, tests, docs and tickets. If it's truly your call, you get plain words and a recommendation.

Don't bother the boss with what the code already says.

13 specialist reviewers

Security, Finance, Compliance, Tester, QA, UI/UX, Clean code, DBA, Ops, Perf, Data, Design, Marketing — picked by the topic, in parallel, after Verify passes.

Thirteen cousins with opinions. Useful ones, for once.

Git agent + Git guard

One agent owns every commit, merge, PR and tag. Force pushes, hard resets and history rewrites outside it get a warning — or a hard no.

“push --force? I hid the car keys.”

Work memo & resume

A small memo per project: now, next, what needs you. After a break or a /compact you get a short resume block, not a re-read of everything.

He remembers who owes what. Forever.

Context watch

Warns at 500K, 600K … 950K tokens of context and stops the work once at your mark, so you compact at a task boundary, not mid-thought.

A full house costs more. He'll tell you when to tidy.

New in 2.13.0

Prompt checkup

Checks every agent brief before it starts: header, files, a real “done when”. Flags risky asks — money, auth, prod — that name no file or end state.

A vague brief costs money. He sends it back.

Sub-session routing

Side sessions started from the desktop app get a model and effort by tier too — and a cap on how many stay open.

Even the kids get a budget.

Scrum agent

Refines stories, splits epics, plans sprints and keeps tickets in step with the code in Jira, Linear, ClickUp and more. Writes only when you said so.

Runs the standup. Doesn't let it run long.

Real receipt

Not a guess. The bill.

The hook reads each subagent's own transcript and prices every billed token at list prices. This is the actual receipt from shipping version 2.13.0 — the uncle shipped himself.

Where receipts live in the pane
The pane

His ledger, beside your chat.

The optional abofles-guide mod adds a pane to the Claude desktop app: what to do next, what's running, where you left off, what every agent cost, and an editor for every setting. Real screens — nothing mocked.

Pane Home page: Next up, At a glance context meter, Tasks card at step 2 of 7, Agents 24% saved.
HomeThe one thing to do next, the context meter and your task list.
Pane Agents page: 24% saved, $3.27 of $4.30 on Opus 5.5, split by Haiku, Sonnet and Opus, and the agent history.
AgentsWhat was saved, the spend by model, and every agent's cost.
Pane Overrides page: 13 settings set for all projects, like Main session opus.medium and Git guard deny.
OverridesEvery setting you changed, and an editor for the rest.
1,317topics he knows
31domains, code to ads
23agents in the family
13specialist reviewers
30versions shipped
FAQ

Questions the uncle gets at dinner.

Is it free?

Yes. Open source under MIT. No account, no sign-up, no “pro” tier. He'd never charge family.

Does it make Claude worse to save money?

No. With the default Matrix = quality, Opus writes, plans and analyses at every tier. Haiku and Sonnet only read and check. A FAIL or low confidence escalates one step at a time to a stronger setting.

Does it send my data anywhere?

No. The only network call is the optional update check: GitHub's public releases list, at most every 6 hours, none of your data. Update check = off turns it off. Ledgers and the memo stay on your machine.

I'm a designer / marketer. Is this for me?

Yes. Graphic design, video and motion, 3D and social and ads have their own topics and reviewers. It never posts, schedules or spends on its own — you press the button.

Which systems does it run on?

macOS, Linux and Windows (with Git Bash, which Claude Code uses there). It needs Python 3.8+ on the PATH. Without Python the hooks step aside and the skill still routes.

Is it made by Anthropic?

No. It's an independent open-source plugin for Claude Code, not made or endorsed by Anthropic.

What does “Abo Fles” even mean?

In Iraqi slang, ابو فليس is the stingy uncle who counts every fils — a thousandth of a dinar. You know the one. This plugin counts every token.

Let the uncle hold the wallet.

Two lines in Claude Code. Free forever. He's already counting.

/plugin marketplace add Sajadh92/abofles
/plugin install abofles@sajadh92