Production Readiness Audit: five rules and a five-check script (free sample)
by PaperChaseWebb
From the Production Readiness Audit: five rules for going live (a pass needs evidence, every gap has an owner and a due date, roll back once on purpose, test refusals, someone who did not build it signs), and a read-only script that checks one audit file for them.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 5 min
- Format
- .md file
production-readiness-audit-five-rules-and-checks-free-sample.md · 7 KB · direct download, no signup
What you end up with
In a few minutes you can see whether an agent system's go-live rests on proof or on ticked boxes.
What you get
- Five go-live rules
- audit_mini.py: five read-only checks on one audit-lite.json
- One prompt for all four harnesses
- Worked example: 5 findings, then 0
Who it is for
Anyone who wants a quick, honest check before an agent workflow goes live.
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
Read audit-lite.json. For each area marked pass, open the evidence file it names and tell me in one line whether it actually proves the area. Mark any that do not as gap. Run audit_mini.py audit-lite.json and show me the findings. Do not sign anything.
The rules and the script are in the file.
Free preview of the file
# Production Readiness Audit: five rules and a five-check script (free sample)
Version 1.0, 2026-10-28. By PaperChaseWebb. For anyone about to put an agent workflow in front of real customers, built with Grok Bot, Claude Code, Codex, Hermes or anything else. 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 system.
Readiness checklists are easy to pass. "Rollback plan: yes." "Error handling: yes." Signed by the person who built it. The problems show up later: a rollback nobody had tried, a gap nobody owned, an agent that did whatever an email told it to. These five rules ask for proof on the points that hurt 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('audit_mini.py','w').write(re.search(r'~~~python\n(.*?)~~~',t,re.S).group(1))"
python3 audit_mini.py audit-lite.json
```
## Five rules
1. **A pass needs evidence.** Name a file: a config excerpt, a log sample, a test output, a drill note. "Works" and "tested" are not evidence.
2. **Every gap has a named owner and a due date.** Not "TBD", not "the team".
3. **Roll back once on purpose before launch.** Write down the date it passed.
4. **Test refusals.** Give the agent something it must decline (a price it should not promise, an Worth knowing
- The sample checks one file against five rules. The twelve areas, evidence folder, blocking areas, secrets and access sheets, monitors, the seal, owner approval by hash and the fifteen checks are in the full pack.
- On 2026-10-28 audit_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 audit folder with twelve areas and templates, what counts as evidence for each, audit.py with the seal and owner approval tied to the report hash, fifteen read-only checks with a seeded test audit, a skill file, AGENTS.md snippet and Grok Bot rules block, ten prompts and a failure table. $39.
Details
Version 1.0 · Updated Oct 28, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related
Production Readiness Audit: decide from evidence whether an agent system can go live
Twelve areas, each pass, gap or na, and every pass points to a dated evidence file. Gaps get a named owner and a due date, five areas block go-live until fixed, drills are run rather than described, and the verdict is signed by someone who did not build the system. A fifteen-check script reads the folder, the report is sealed to a hash of the evidence, and the owner's go-live yes is tied to the report's sha256.
Install Binder: five go-live rules and a five-check script (free sample)
From the Agency Install Kit: five rules to meet before an agent workflow goes live (a named owner per agent, a tested pause, a gate on every risky action, a dry run with a refusal case, a kill rule), and a read-only script that checks one small file for them.
Agent Readiness Self-Check: score one workflow before you hand it to an AI agent
A free self-check for agencies and small businesses. Score one workflow across eight areas (workflow mapped, data access, approval gates, owner per agent, handoffs, cost tracking, security and vetting, measurement) with an evidence rule and three gate rules, read your band and what to do next, plus an interview prompt for Grok Bot, Claude Code, Codex or Hermes, a score sheet and a worked example.