# 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.

- URL: https://paperchasewebb.ai/bots/marketplace/items/evidence-standard-five-rules-and-checks-free-sample/
- Type: Prompt pack
- Category: Solo business
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Grok Bot, Hermes (named in the listing); Plain .md plus one Python 3 script, standard library only; one prompt for all four harnesses
- Price: Free USD
- Difficulty: Beginner
- Setup time: 5 min
- Time to result: About five minutes to a first result
- Format: Markdown (.md) file, evidence-standard-five-rules-and-checks-free-sample.md
- Version: 1.0, updated 2026-10-29
- License: Personal and commercial use.

## What you end up with

In a few minutes you can see whether the done in your agents' reports rests on evidence someone else can open, or on the agent's word.

## What you get

- Five evidence rules
- evidence_mini.py: five read-only checks on one evidence-lite.json
- One prompt for all four harnesses
- Worked example: 5 findings, then 0

## Who it is for

Anyone who wants a quick check of what their agents count as proof before trusting their reports with more.

## Tools needed

- Grok Bot, Claude Code, Codex or Hermes: the agent that does the work; it reads the skill file, AGENTS.md snippet or rules block, logs each claim with its evidence, seals it with evidence.py seal and reports in the words evidence.py say gives
- Python 3: runs evidence.py (init, hash, seal, say, report, owner approval, verify, done) and the fifteen-check checker; standard library only, no network
- You need: Python 3.9 or newer
- You need: Any of Grok Bot, Claude Code, Codex or Hermes

Cost to run: Free.

## Sample prompt: Find the claims with no proof (Grok Bot, Claude Code, Codex, Hermes)

```
List every time in this session, or the last one you can see, where you said something was done, fixed, passing, sent or live. For each, write what proof exists that I can open myself right now: a file, an output, a link with the line, or nothing. Mark the ones where the only proof is your own summary. Change nothing.
Run evidence_mini.py evidence-lite.json and show me the findings.
```

The rules and the script are in the file.

## Free preview of evidence-standard-five-rules-and-checks-free-sample.md

````markdown
# Evidence Standard: five rules and a five-check script (free sample)

Version 1.0, 2026-10-29. By PaperChaseWebb. For anyone who lets an agent report work as done, in Grok Bot, Claude Code, Codex, Hermes or a mix, and wants a written rule for what counts as proof before that word gets used. One Markdown file and one Python 3 script, standard library only. The script was tested on its worked example (5 findings, then 0) and on a missing file (exit 2). It was not run inside any agent harness or on a real team's work.

An agent says the tests pass. Sometimes they do. Sometimes the test was a stub, the run was from before the last edit, or no run happened at all and the sentence came from the plan. The fix is not a better prompt. It is a short written standard: for each kind of work, what counts as proof, who checks it, and what is refused. These five rules cover the gaps that cost the most, and the script checks them in one small file.

## Install in one line

Save this page as FREE-SAMPLE.md, then:

```
python3 -c "import re;t=open('FREE-SAMPLE.md').read();open('evidence_mini.py','w').write(re.search(r'~~~python\n(.*?)~~~',t,re.S).group(1))"
python3 evidence_mini.py evidence-lite.json
```

## Five rules

1. **A person owns the standard.** Someone decides what proof means for this team. Not "TBD", and not the agent whose work is being checked.
2. **Every class of work names its proof and its checker.** Code changes, research claims, outreach drafts and releases each get their o
````

## Test record

- Date: Oct 29, 2026
- What was run: evidence_mini.py on the worked example, a fixed file and a missing file.
- Result: 5 findings, then 0; exit 2 on a missing file.
- Not run: The prompt inside a harness.

Copied from this item's dated test notes. What was not run stays in.

## Worth knowing

- The sample checks one file against five rules. The five-file standard, proof kinds, refusals, sealed evidence, say and its claim ladder, owner approvals by hash and the fifteen checks are in the full pack.
- On 2026-10-29 evidence_mini.py gave 5 findings on the worked example, then 0 on the fixed file, and exited 2 on a missing file. The prompt was not run inside a harness.

## Questions

**Does it send anything anywhere?** No. It reads one file and opens no network connection.

**What is in the full pack?** The five-file standard with templates, evidence.py that seals evidence and tells your agents what they may say, owner approvals tied to a hash with one use and expiry, fifteen read-only checks with a seeded test standard, a skill file, AGENTS.md snippet and Grok Bot rules block, ten prompts and a failure table. $24.

## How to get it

Free sample. Download it directly at https://paperchasewebb.ai/bots/marketplace/items/evidence-standard-five-rules-and-checks-free-sample/, no signup.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com