coldpass

Per-setup public labels: Linux / Luna: Works

Static status badge · SVG · read-only JSON. Embed with ![Coldpass status](https://coldpass.dev/badge/s0undt3ch--ToolR.svg).

coding

Works

The recorded run passed on 1 setup.

Answers apply to each recorded setup, revision and operation. Earlier observations remain in Run details.

Tested on Linux
PlatformHaikuLuna
Linuxour test failed; no repo verdictyes

Linux / Haiku 5.5: our test failed; no repo verdict · Oct 27, 2026 · 456284c04647
Recorded operation: No working operation verified.

Linux / Luna: yes · Oct 27, 2026 · 456284c04647 · codex / codex-cli 0.164.0
Recorded operation: /tmp/toolr-venv/bin/toolr example hello --name Coldpass

Does what it says
1 of 1 claims checked out
  • Run the generated hello example with a supplied name.: Real input produced the expected result: hello, Coldpass

    Source: toolr example hello # run the generated example

    Input: --name Coldpass

    Expected: hello, Coldpass

    Command: /tmp/toolr-venv/bin/toolr example hello --name Coldpass

    Observed: hello, Coldpass

MCP
No
Local or hosted
both local and hosted
Both a local install and a hosted service
Needs keys or browser
None seen
Maintained
Maintained
actively maintained: last commit 0 days ago; 549 commits and 146 merged PRs in 90 days; 9 open issues, 3 open PRs; latest release 2026-10-27

Last commit Oct 27, 2026

Setup time
44 s
44 s to a working result
Issue
none found in recorded check
Examples
1 of 1 ran as expected
  • Scaffold a project and run its generated hello command.: command completed successfully

    Source: README.md / Scaffold your repo

    Input: toolr project init; toolr example hello

    Expected: hello, world

    Command: /tmp/toolr-venv/bin/toolr example hello

    Observed: hello, world

Evidence
README behavior checked
Agent interfaces
CLI
CLI

Observed interfaces were exercised by the checker. Documentation alone does not confirm compatibility.

Tested with
Codex / Luna
  • Linux: Codex / Luna · agent codex-cli 0.164.0 · Checked operation passed · Oct 27, 2026 on 456284c04647

Each entry describes its recorded operation and source revision.

Safety
No unexpected network or file activity found in these checks

No problems traced to this repository code in these checks; a short run cannot prove safety. 4 listed items (named-host connections, static matches, dependency advisories) are below and do not change this verdict.

Source contains download and execute; review its purpose. installation/install.sh 2 findings.

Reviewed as expected for a test run: attempted writes that failed, so nothing was written.

Full event, path and process lists for each observed setup:

Repair history and test corrections
Current diagnosis: test · test rerun did not pass

native Claude returned a different model

Recorded action: Diagnose the linked test rerun evidence.

Repair record fix-dc7ee8d6a415921e9f09 · current status JSON. Original run outcomes remain unchanged.

Failed run: s0undt3ch/ToolR · Oct 27, 2026 · Our test failed; no repo verdict.

Test-repair rerun: s0undt3ch/ToolR · Oct 27, 2026 · Our test failed; no repo verdict.

Current diagnosis: test · test rerun did not pass

native Claude returned a different model

Recorded action: Diagnose the linked test rerun evidence.

Repair record fix-8995bafe300e10211bd2 · current status JSON. Original run outcomes remain unchanged.

Failed run: s0undt3ch/ToolR · Oct 27, 2026 · Our test failed; no repo verdict.

Test-repair rerun: s0undt3ch/ToolR · Oct 27, 2026 · Our test failed; no repo verdict.

Run details
Earlier attempts (1)

Luna

Native agent · Checked operation passed

Checked operation /tmp/toolr-venv/bin/toolr example hello --name Coldpass

Agent-reported scope: toolr project init and generated example hello

Run details
run
s0undt3ch--ToolR-gpt-6-luna-1793113929372410276
date
Oct 27, 2026
time to working
43.9s
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
gpt-6-luna
agent / version
codex / codex-cli 0.164.0
platform
linux
reported cost
not reported (not assumed free)
Recorded source
https://github.com/s0undt3ch/ToolR
Backend
hyperv
Tool transport
mcp-assigned-vm
Requested source pin (not an observed revision)
{"commit": "456284c0464711423bffdec6a805d2595b227f82", "url": "https://github.com/s0undt3ch/ToolR"}
Test version
readme-38e6b13f3b13804effb95797e3466b1a1334da7a232d897cbc8965867f802605
revision
456284c0464711423bffdec6a805d2595b227f82
Whose fault: not assigned · resolved

Safety: Review signals: 2 download and execute.

Review signals: 2 download and execute.

Reviewed as expected for a test run: attempted writes that failed, so nothing was written.

Source contains download and execute; review its purpose. installation/install.sh 2 findings.

OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check.

A short run cannot establish that code is safe.

Connections show IP addresses; proxies can hide the final hostname.

Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing.

Full safety evidence →

Answers recorded for this run
  • Run the generated hello example with a supplied name.: Real input produced the expected result: hello, Coldpass

    Source: toolr example hello # run the generated example

    Input: --name Coldpass

    Expected: hello, Coldpass

    Command: /tmp/toolr-venv/bin/toolr example hello --name Coldpass

    Observed: hello, Coldpass

Examples

  • Scaffold a project and run its generated hello command.: command completed successfully

    Source: README.md / Scaffold your repo

    Input: toolr project init; toolr example hello

    Expected: hello, world

    Command: /tmp/toolr-venv/bin/toolr example hello

    Observed: hello, world

Local or hosted: both

What the agent did

toolr project init and generated example hello

pwd && ls -la && sed -n '1,240p' README.md && python3 --version
which toolr || true; which uv || true; python3 -m pip --version; rg -n "toolr|python" .github/workflows pyproject.toml Cargo.toml | head -60; ls -la .coldpass
python3 -m pip install --user toolr
python3 -m venv /tmp/toolr-venv && /tmp/toolr-venv/bin/pip install toolr
mkdir -p .coldpass && /tmp/toolr-venv/bin/toolr project init
find tools -maxdepth 2 -type f -print; sed -n '1,200p' tools/pyproject.toml; /tmp/toolr-venv/bin/toolr --help
mkdir -p /tmp/toolr-probe; cd /tmp/toolr-probe && /tmp/toolr-venv/bin/toolr project init && /tmp/toolr-venv/bin/toolr example hello
cat > .coldpass/probe.json <<'EOF'
{"kind":"cli","argv":["/tmp/toolr-venv/bin/toolr","example","hello","--name","Coldpass"],"cwd":"/tmp/toolr-probe","expected_text":"hello, Coldpass"}
EOF
cat > .coldpass/claims.json <<'EOF'
[{"kind":"claim","claim":"Run the generated hello example with a supplied name.","source":"toolr example hello                 # run the generated example","input":"--name Coldpass","expected":"hello, Coldpass","probe_kind":"cli","argv":["/tmp/toolr-venv/bin/toolr","example","hello","--name","Coldpass"],"expected_text":"hello, Coldpass","cwd":"/tmp/toolr-probe"}]
EOF
cat > .coldpass/examples.json <<'EOF'
[{"kind":"example","claim":"Scaffold a project and run its generated hello command.","source":"README.md / Scaffold your repo","input":"toolr project init; toolr example hello","expected":"hello, world","argv":["/tmp/toolr-venv/bin/toolr","example","hello"],"cwd":"/tmp/toolr-probe","expected_text":"hello, world"}]
EOF
cat > .coldpass/cycles.json <<'EOF'
{"detected":false,"reason":"Inspected README and CLI overview; ToolR runs explicitly invoked task commands and documents no scheduler or recurring product cycle.","checks":[]}
EOF
python3 - <<'PY'
import json
p='.coldpass/report.json'
d={'outcome':'working','fault_owner':None,'operation':'toolr project init and generated example hello','operation_scope':'Installed ToolR 0.35.1 in a Python 3.12.3 virtual environment; scaffolded a fresh project and invoked its hello command.','steps':['Read README install and scaffold instructions.','Installed toolr with pip in /tmp/toolr-venv.','Ran toolr project init in /tmp/toolr-probe.','Ran toolr example hello; output was hello, world.'],'deviations':['Initial pip --user install failed with externally-managed-environment; retried successfully in a venv.','Init in repository could not proceed because tools/pyproject.toml already exists; used a fresh temporary project directory.'],'stuck_step':None,'main_blocker':None,'plain_failure':None,'suggested_fix':None}
open(p,'w').write(json.dumps(d,indent=2)+'\n')
PY
<env-var>=<guest-path> python3 -I <guest-path> --validate --replay

No product verdict. Run record.

No product verdict. Run record.

No product verdict. Run record.

No product verdict. Run record.