Test a token-saving prompt against hidden tests before you adopt it

What you end up with

32 runs is a small sample and the numbers are his own.

What you get

• A plain-language summary of the workflow
• A fill-in prompt template
• What to watch out for
• A link to the original source

Who it is for

Builders who already use AI agents and want a proven workflow they can copy into their own project.

Works with

Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.

Tools needed

Cost to run: Free with the agent plan you already use.
Time to result: One working session

How it works

1. Pick 8 or more real tasks across types: bug fix, feature, review

   Pick 8 or more real tasks across types: bug fix, feature, review.

   Expected: Done before you move to the next step.

2. Write hidden tests for each that the agent cannot see

   Write hidden tests for each that the agent cannot see.

   Expected: Done before you move to the next step.

3. Run each task with and without the prompt, several times

   Run each task with and without the prompt, several times.

   Expected: Done before you move to the next step.

4. Compare cost and pass rate per task type

   Compare cost and pass rate per task type.

   Expected: Done before you move to the next step.

5. Adopt the prompt only where it saves money without losing quality

   Adopt the prompt only where it saves money without losing quality.

   Expected: Done before you move to the next step.

Sample prompt from the pack

Apply this workflow to [your project]:
1. Pick 8 or more real tasks across types: bug fix, feature, review.
2. Write hidden tests for each that the agent cannot see.
3. Run each task with and without the prompt, several times.
4. Compare cost and pass rate per task type.
5. Adopt the prompt only where it saves money without losing quality.
Stop and ask me before anything irreversible: deploys, payments, sends or deletes.

Free preview of the file

# Test a token-saving prompt against hidden tests before you adopt it

PaperChase agent use case (free feed entry), version 1.0. Source: [@mano_sec](https://x.com/mano_sec/status/2115571933899116804), 2026-10-28.

## What they did

He compared runs with and without the prompt across task types and checked results with tests the agent could not see. Savings were real but small, and concentrated where the agent writes a lot of prose (reviews), not where it reads a lot of code (bug fixes).

## Worth knowing

32 runs is a small sample and the numbers are his own. The method is what to copy: same tasks, with and without, hidden tests for quality, cost per task type. A separate builder claims 3 to 4 times fewer tokens by asking for a fresh-context follow-up prompt instead of compacting, which is self-reported and worth testing the same way.

Worth knowing

• 32 runs is a small sample and the numbers are his own. The method is what to copy: same tasks, with and without, hidden tests for quality, cost per task type. A separate builder claims 3 to 4 times fewer tokens by asking for a fresh-context follow-up prompt instead of compacting, which is self-reported and worth testing the same way.
• Figures are as reported by the original author and were not re-measured by us.

Details

Version 1.0 · Updated Oct 29, 2026 · Markdown version of this page
License: Personal and commercial use. Credit the original source when you share the workflow. Download terms

Related

Prompt pack$14

AGENTS.md, CLAUDE.md and Cursor rules starter files

by PaperChaseWebb

Six fill-in instruction files for coding agents (base, Next.js plus Supabase, FastAPI, browser game, CLAUDE.md pointer, scoped Cursor rules), an Approvals section that makes the agent stop and wait for your yes, a table of what Grok Bot, Claude Code, Codex, Hermes and Cursor each read, a read-only checker for your rule files and 9 prompts to write, trim and test your own.

Works withClaude CodeCodexGrok BotHermes+1Plain .md and one Python 3 file (standard library only). Section 6a lists what Claude Code, Codex, Hermes and Cursor read, from their docs read 2026-10-30, and a block to paste into Grok Bot. The files were not run inside each tool.

Vibe coding · Beginner · 20 min setup

Prompt pack$19

Ask-first rules for AI agents: hard nos, approval cards and a test set

by PaperChaseWebb

Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.

Works withClaude CodeCodexClaudeGrok Bot+4Plain .md plus one Python 3 file, standard library only. The agent prompt in block 13 is written for any agent with a shell (Grok Bot, Claude Code, Codex, Hermes); it was not loaded inside each harness.

Solo business · Beginner · 20 min setup