Replicate Before You React: a claim card, five rules and a rate script (free sample)
by PaperChaseWebb
From Replicate Before You React: a ten-line claim card to fill in before you test a claim about your agent, five safety rules (canary never payload, throwaway environment, one capped key, a control arm, say what you ran) and a script that shows how much a handful of runs can actually tell you.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 5 min
- Format
- .md file
replicate-before-you-react-claim-card-free-sample.md · 5 KB · direct download, no signup
What you end up with
In a few minutes you know what a claim leaves out, how to test it safely, and whether 3 hits in 20 runs says anything about a claimed 90%.
What you get
- A ten-line claim card
- Five safety rules
- rate_mini.py: a rate with a 95% Wilson interval and a verdict against the claimed rate
- A table of what a few runs can tell you
Who it is for
Anyone who wants a quick, safe way to size up a claim about their agent before acting on it.
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.
Time to result: About five minutes to a first result
Sample prompts, free to use
Here is a post about an agent. Fill the claim card from FREE-SAMPLE.md in your own words. Write not stated for anything the post does not say. Do not quote the post and do not run anything.
The card, rules and script are in the file.
Free preview of the file
# Replicate Before You React: a claim card, five rules and a rate script (free sample)
Version 1.0, 2026-10-29. By PaperChaseWebb. For developers and small teams who keep getting forwarded posts about coding agents (a security hole, a token saver, a hidden cost) and want to test the claim before changing anything. One Markdown file and one Python 3 script, standard library only. The script was tested on three inputs and a bad input (exit 2). It was not run inside any agent harness or against a live agent.
Posts about agents arrive daily: one says a file in your Downloads folder hijacks the agent nine times in ten, another says one rule cuts tokens by 40%. Some hold up, some held for one version, and some were one lucky run. The step between ignoring them and acting on them is cheap: run the claim yourself, safely, enough times to know. This sample gives you the card to fill in, the rules that keep it safe, and a script that tells you how much a handful of runs can actually say.
## Install in one line
Save this page as FREE-SAMPLE.md, then:
```
python3 -c "import re;t=open('FREE-SAMPLE.md').read();open('rate_mini.py','w').write(re.search(r'~~~python\n(.*?)~~~',t,re.S).group(1))"
python3 rate_mini.py 3 20 0.9
```
## The claim card
Fill this in before any run. If you cannot fill a line, write "not stated".
| Line | Your answer |
|---|---|
| The claim, in your own words, one sentence | |
| Source link and date | |
| Agents and versions the source tested | |
| Settings or Test record
- Date
- Oct 29, 2026
- What was run
- rate_mini.py on four inputs and a bad input, and the copy taken from the sample page.
- Result
- Exit 2 on the bad input; the copy ran the same.
- Not run
- Any agent harness or a live agent.
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- The sample sizes up a claim and reads a result. The plan templates, the container runner, the ten checks, cost intervals with a control arm, the result card and the tests are in the full pack.
- On 2026-10-29 rate_mini.py was run on four inputs and a bad input (exit 2), and the copy extracted from the sample page ran the same. It was not run inside any agent harness or against a live agent.
Questions
Does it run anything against my agent?
No. It does arithmetic on the numbers you give it and opens no network connection.
What is in the full pack?
Plan templates for security, cost and quality claims, a runner that does each run in a fresh container, trials.py with ten checks, intervals and a result card, a skill file for Claude Code and Codex, two worked examples, eight prompts and the tests. $19.
Details
Version 1.0 · Updated Oct 29, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related
Replicate Before You React: a trial kit for claims about AI agents
Test a claim about a coding agent on your own setup before you change anything: a security hole, a token-saving prompt, a hidden cost, a skill that makes the agent better. Restate the claim, run each setup 10 to 20 times in fresh containers with one capped key, use a harmless canary instead of a real payload, run a control arm for cost and quality, and get rates with honest intervals and a result card that says what you did not test.
Check the Claim: the six questions (free sample)
Six questions, an evidence level label, the add-the-parts check, one prompt and one card template that make any agent with web search check a claim before you use it. Updated to v1.1.
Vet Before You Install: the twelve checks (free sample)
The seat sort and the twelve checks to run before any third-party skill, plugin, MCP server, repo or model touches a real machine, plus one prompt and the decision line. Updated to v1.1.
Evidence Standard: five rules and a five-check script (free sample)
From the Evidence Standard: five rules for what your agents may call done (a person owns the standard, every class of work names its proof and its checker, the agent's own account is never proof, people, money, records and releases are checked by a person, nobody says done on their own work), and a read-only script that checks one small file for them.