# 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.

- URL: https://paperchasewebb.ai/bots/marketplace/items/pinned-trial-method-test-a-new-skill-at-one-commit-in-a-proven-sandbox/
- Type: Prompt pack
- Category: Vibe coding
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Grok Bot, Hermes (named in the listing); One shell script, four Python scripts, a record template, AGENTS.md and CLAUDE.md rules, a skill file, a Grok Bot standing order and Codex and Hermes notes. The sandbox needs Linux or WSL2
- Price: $24 USD
- Difficulty: Intermediate
- Setup time: 20 min
- Time to result: First trial in about 30 minutes on the quick profile
- Format: Markdown (.md) file, pinned-trial-method-test-a-new-skill-at-one-commit-in-a-proven-sandbox.md
- Version: 1.0, updated 2026-11-03
- License: Use for yourself, your team or your clients. Do not resell or republish the kit itself.

## What you end up with

A tool trial anyone can repeat: the exact commit, proof the sandbox held, proof the target did not change, and a signed ADOPT, HOLD or REJECT.

## What you get

- sandbox_run.sh: one command in bubblewrap with the host read-only, home hidden, network off, env cleared and one writable folder, with CPU, memory and wall-clock limits by profile
- Four probes that run first and stop the trial if the sandbox does not hold
- tree_hash.py: one sha256 for the whole target, so an unchanged target is a fact
- leak_scan.py: finds the planted dummy key anywhere the tool wrote it
- trial_check.py: 21 error checks and 2 warnings on the trial record, read-only
- The seven-step method, three profiles and a blank trial record
- AGENTS.md, CLAUDE.md, a pinned-trial skill, a Grok Bot standing order, Codex and Hermes notes
- 24 tests, including a hostile tool that tries to rewrite the target, write to /etc, reach the network and copy the key

## Who it is for

Anyone who wants a hands-on tool trial they can repeat and defend, with a person making the final call.

## Tools needed

- Linux or WSL2 with bubblewrap: the sandbox: host read-only, network off, env cleared, limits set
- Python 3.8 or newer: tree hash, leak scan, probes and the record checker; standard library only
- Grok Bot, Claude Code, Codex or Hermes (optional): runs the trial under AGENTS.md and proposes a call; never adopts, uses real keys or turns the network on
- You need: Linux or WSL2 with bubblewrap installed
- You need: Python 3.8 or newer
- You need: git

Cost to run: The kit is the only purchase. bubblewrap and Python are free.

## How it works

1. **Run the tests.** Unpack the kit, install bubblewrap and run python3 -m unittest discover -s tests. Expected: 24 tests pass, including the hostile tool tests.
2. **Pin and read.** Clone the tool from its official address, check out one full commit, confirm it with git rev-parse HEAD and read every instruction file it gives an agent. Expected: A commit, a license and a list of flagged instructions in the record.
3. **Hash, then run in the sandbox.** Hash the target with tree_hash.py, then run the tool through sandbox_run.sh on the quick profile. Expected: probes.json with four true values and the tool's output in the run folder.
4. **Check and sign.** Hash the target again, run leak_scan.py, fill the record and run trial_check.py. A named person signs the call. Expected: CLEAN from the checker and a signed verdict.

## Sample prompt: Start a trial (Grok Bot, Claude Code, Codex, Hermes)

```
Follow AGENTS.md in this kit. Trial <tool> from <official URL> at commit <hash> against <target folder> on the quick profile. Stop after trial_check.py and give me its output, your proposed call, and what you did not test.
```

Prompt 1 of 2.

## Sample prompt: Review someone else's trial (Grok Bot, Claude Code, Codex, Hermes)

```
Read trial.json and the files in its evidence list. Tell me whether the evidence supports the call, and list anything the record claims that the files do not show.
```

Prompt 2 of 2.

## Free preview of pinned-trial-method-test-a-new-skill-at-one-commit-in-a-proven-sandbox.md

````markdown
# Pinned Trial Method

**Try a new skill or repo once, at one exact commit, in a sandbox you have proven, against a folder it cannot change. End with a verdict you can defend and a person's signature on it.**

Version 1.0, 2026-11-03. By PaperChaseWebb Inc. Works with Grok Bot, Claude Code, Codex and Hermes, or on its own. Linux or WSL2 for the sandbox; the checkers run anywhere with Python 3.8 or newer.

## The problem

Reading a tool's README tells you what it claims. It does not tell you what it does when it runs. Most "we tried it" notes leave out the version, where it ran, whether it touched anything, and who decided. Two weeks later nobody can repeat the test or explain the yes.

## What you end with

One trial record per tool, checked by a script, with four facts nobody has to take on trust:

1. **The exact code.** A full 40-character commit, confirmed after checkout, plus its license.
2. **A proven sandbox.** Four probes pass before the tool runs: network blocked, host read-only, environment cleared of real keys, limits set.
3. **An untouched target.** One sha256 of the whole target folder before and after. They match or the trial says so.
4. **A signed call.** ADOPT, ADOPT WITH LIMITS, HOLD or REJECT, with evidence files, what was not tested, and a named person who approved. The agent never signs.

## Who it is for

- Teams adding agent skills and MCP servers faster than anyone can read them
- Agencies that install tools for clients and need a record of what was test
````

## Test record

- Date: Nov 3, 2026
- What was run: tests/test_trial_check.py and tests/test_desk.py (24 tests) on Linux with bubblewrap, Python 3.8, 3.9, 3.11, 3.12 and 3.13, including a hostile tool run inside the sandbox; the free sample unpacked from its file and run fresh.
- Result: 24 passed, 0 failed on all five versions; each of the 21 record faults caught by its own code; the hostile tool changed nothing and its copied key was found.
- Not run: macOS or Windows. WSL2. A live Grok Bot, Claude Code, Codex or Hermes session.

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

## Worth knowing

- The sandbox guards against honest mistakes and overreaching instructions. It is not a malware lab; do not trial code you already suspect is hostile on a machine that matters.
- Tools that need the network to work at all cannot be judged in this sandbox. Record them as HOLD and plan a separate, approved test.
- The sandbox script needs Linux or WSL2 with bubblewrap. The Python checkers run anywhere.
- The memory limit counts virtual memory, so some runtimes need the standard profile.
- On 2026-11-03: 24 tests passed on Python 3.8, 3.9, 3.11, 3.12 and 3.13 on Linux with bubblewrap. Agent rules guide; they are not a lock.

## Questions

**How is this different from Vet Before You Install?** Vet Before You Install is the read-only review you do first. This is the hands-on run after it, with proof the sandbox held and the target did not change.

**Can my agent run the trial?** Yes. It can pin, read, run the sandbox and fill the record. It cannot sign the adoption; the checker fails a record where the runner approved itself.

**Does it work on a Mac?** The checkers do. The sandbox script needs Linux, so on a Mac use a Linux VM or a cloud box.

**What does a trial cost?** Nothing beyond the kit. The record makes you write the money and minutes the run took, and zero is a valid answer.

## How to buy

$24 one time at https://paperchasewebb.ai/bots/marketplace/items/pinned-trial-method-test-a-new-skill-at-one-commit-in-a-proven-sandbox/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com