Pinned Trial Method: the trial record checker (free sample)
by PaperChaseWebb
The read-only checker and a clean example record from Pinned Trial Method. Fill in a record after any hands-on test of a new skill or repo and see what it is missing: the pinned commit, sandbox proof, an unchanged target, a leak scan or a person's sign-off.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 5 min
- Format
- .md file
pinned-trial-method-trial-record-checker-free-sample.md · 8 KB · direct download, no signup
What you end up with
You find the holes in a tool trial before anyone acts on it.
What you get
- trial_check.py: 21 error checks and 2 warnings, read-only
- A clean example record
- One prompt for your agent
Who it is for
Anyone who wants a quick check on a tool trial write-up.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: One Python script and one JSON example. Tested on Linux.
Tools needed
Cost to run: Free.
Time to result: About five minutes
Sample prompts, free to use
Run python3 trial_check.py trial.json and explain each finding in one line. Do not fill owner_approval.
The script and the example are in the file.
Free preview of the file
# Pinned Trial Method: the trial checker (free sample)
By PaperChaseWebb Inc. Works with Grok Bot, Claude Code, Codex and Hermes.
After any hands-on test of a new skill or repo, fill in a trial record and run:
python3 trial_check.py trial.json
It fails a record with no pinned commit, no sandbox proof, a target that changed, a leaked key, or an adoption nobody signed. Standard library only. It only reads the file. Exit 0 means clean, 1 means errors, 2 means it could not read the record.
Save the two files below, then run it on the example to see a clean result. Change the commit to `main` and run it again to see T02.
The full kit ($24) adds the sandbox script with its four probes, the folder hash, the leak scan, agent rules for all four harnesses, a blank template and 24 tests.
#### file: desk/trial_check.py
~~~~python
#!/usr/bin/env python3
"""Pinned Trial Method: check a trial record before anyone acts on its verdict.
Usage: python3 trial_check.py trial.json [--strict]
Standard library only. Read-only: it never runs the tool under trial.
Exit 0 = clean, 1 = errors found, 2 = could not read the record."""
import json, re, sys
VERDICTS = {"ADOPT", "ADOPT WITH LIMITS", "HOLD", "REJECT"}
SHA = re.compile(r"^[0-9a-f]{40}$")
HEX64 = re.compile(r"^[0-9a-f]{64}$")
REQUIRED_PROBES = ("network_blocked", "host_read_only", "env_scrubbed", "limits_set")
def check(r):
E, W = [], []
def err(code, msg): E.append((code, msg))
def warn(code, msg): W.append((code, msg)Test record
- Date
- Nov 3, 2026
- What was run
- trial_check.py unpacked from the sample file and run on the example; tests/test_trial_check.py on Linux, Python 3.8, 3.9, 3.11, 3.12 and 3.13.
- Result
- CLEAN on the example; 7 checker tests passed on all five versions.
- Not run
- Everything the full kit does.
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- The sample only reads the record. The sandbox script, probes, folder hash, leak scan, agent rules and tests are in the full kit.
- On 2026-11-03 the checker passed its tests on Linux with Python 3.8 to 3.13.
Questions
Does it run the tool?
No. It reads one JSON file and prints findings.
What is in the full kit?
The bubblewrap sandbox script with four probes, the folder hash, the leak scan, the seven-step method, agent rules for all four harnesses and 24 tests. $24.
Details
Version 1.0 · Updated Nov 3, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related

Pinned Trial Method: test a new skill at one commit, in a proven sandbox
Before a new agent skill, plugin or repo touches real work, run it once at a pinned commit inside a sandbox that proves itself first: network off, host read-only, real keys cleared, limits set. Hash the target before and after, scan the output for a planted dummy key, and end with a checked record and a call a person signs.

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.