Desk Authority Map: five rules and a five-check script (free sample)
by PaperChaseWebb
From the Desk Authority Map: five rules for an agent fleet (every desk has a human owner, no desk checks its own work, nothing that cannot be undone is decided alone, money gets a dollar limit, some actions belong to the owner), and a read-only script that checks one map file for them.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 5 min
- Format
- .md file
desk-authority-map-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 your agents' authority is written down or assumed.
What you get
- Five authority rules
- authority_mini.py: five read-only checks on one authority-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 which agent may do what before giving a fleet more access.
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 authority-lite.json. List every action you have done in the last week that is not in it, and the level you think each should have. Do not change the file. Run authority_mini.py authority-lite.json and show me the findings.
The rules and the script are in the file.
Free preview of the file
# Desk Authority Map: five rules and a five-check script (free sample)
Version 1.0, 2026-10-28. By PaperChaseWebb. For anyone running more than one agent, in Grok Bot, Claude Code, Codex, Hermes or a mix, who wants it written down which agent may do what on its own. 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 fleet.
Most agent setups have an org chart: a research agent, a support agent, a builder. Titles, tools, a reporting line. What the chart rarely says is the part that matters on a bad day: which of them may send, spend, delete or change access without asking, and who checks their work. 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('authority_mini.py','w').write(re.search(r'~~~python\n(.*?)~~~',t,re.S).group(1))"
python3 authority_mini.py authority-lite.json
```
## Five rules
1. **Every desk has a human owner.** A person answers for it. Not "TBD", and not another agent.
2. **No desk checks its own work.** Another desk or a person reads what it did.
3. **Nothing that cannot be undone is decided alone.** A sent email, a deletion, a refund: prepare it, then someone releases it.
4. **Money gets a dollar limit.** If a desk mayTest record
- Date
- Oct 28, 2026
- What was run
- authority_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 four-file map, risk classes, escalation, evidence, the runtime check, owner approvals by hash and the fifteen checks are in the full pack.
- On 2026-10-28 authority_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 four-file map with templates, authority.py that your agents ask before acting, owner approvals tied to a request hash with one use and expiry, fifteen read-only checks with a seeded test map, a skill file, AGENTS.md snippet and Grok Bot rules block, ten prompts and a failure table. $29.
Details
Version 1.0 · Updated Oct 28, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related
Desk Authority Map: who in your agent fleet may decide what
Four plain files say, for every desk and action, decide, propose, ask-owner or never, with dollar limits, escalation and the evidence each desk owes. Agents ask authority.py before they act and get the answer as an exit code; anything not in the map is never. Owner yeses are typed at the owner's terminal, tied to one request's sha256, good for one use, and refused inside an agent. Fifteen read-only checks run on the map itself.
Production Readiness Audit: five rules and a five-check script (free sample)
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.
Agent Readiness Self-Check: score one workflow before you hand it to an AI agent
A free self-check for agencies and small businesses. Name the decision, then 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, three gate rules and a skeptical pass, and read your band and the next steps it allows. v1.1 starts with the decision the score will change, scores unknowns as unknown, adds rules for conflicting facts and lookalike public records, ties every band to the next steps it allows with the Production Readiness Audit before go-live, makes owner approval concrete (prepared and approved status, a one-reply approval line, decisions the agent must leave open, a done test), adds agent files for Grok Bot, Claude Code, Codex and Hermes, a second worked example (missed call to booked job), a readiness folder with a fifteen-check read-only checker, a front door test with four questions to ask anyone selling you an agent install, and a plain note on how it was tested. Still free.