Skip to main content
DanManREAL/ AI_LAB
Updated Nov 20, 2026Request a test

AuditTested AIBy Published Tested Updated

Steps → Reduced: opening a terminal agent went from 98 seconds to 11

The report

Audit

Verdict

98 s → 11 s · 11 round trips → 3

Same agent, same request: claude-deepseek opened a Qoder CLI terminal in 98.2 seconds with my first skill and in 11.4 seconds after the red-team pass. Its model round trips fell from 11 to 3 and its commands from 12 to 2.

On the tier list: A test of my own workshop skill with one agent, so it places no model on the tier list.

claude-deepseek opens Qoder CLIFirst skill (8:00 PM)Rebuilt skill (8:42 PM)
Time, transcript timestamps98.2 s11.4 s
Time, Claude Code's turn timer107.9 s11.5 s
Commands the agent ran122
Round trips to the model113
Window command itself0.516 s2.459 s, checks included

Steps → Reduced

I'm aiming to cut the steps out of every capability in my workshop. Opening a terminal agent was the first: I type OPEN TERMINAL AGENT using a harness name, and whichever agent I'm talking to opens a new Windows Terminal window running that harness. A harness is the command-line program an AI model works inside. It took five steps to get from 98 seconds to 11.

Step 1: 11 steps down to 3, then a skill

With no skill yet, I asked a claude-deepseek agent (Claude Code running deepseek-flash) to open a WSL Ubuntu terminal running Codex. It did, in 74.6 seconds and 18 commands, most of them finding out how. I asked it to list its steps: 11. Then I asked how it could have done it in the fewest steps, and it got it down to 3: open the window, check the new process and its folder, check that a window exists.

Claude Code on deepseek-flash at max effort. My test prompt asks it to open a WSL Ubuntu terminal with codex in the workshop folder. It ran 18 commands with 1 error, then reports a new Windows Terminal Ubuntu window open with codex running, verified by the launch command's exit code, the new codex process and its folder, and a visible window titled Ubuntu.
Step 1, 7:51 PM ET. The first open, with no skill: 18 commands.

I had it turn those 3 steps into a SKILL.md with a trigger for each harness I might want open: Codex, claude-caveman, claude-deepseek, Qoder CLI, Muse, Gemini CLI and Kimi.

The same terminal. I ask it to turn the 3 steps into a SKILL.md triggered by OPEN TERMINAL AGENT followed by using codex, using claude-caveman or using claude-deepseek, then add qodercli, muse and gemini, then kimi.
Step 1. The 3 steps become the OPEN TERMINAL AGENT skill, one trigger per harness.

Step 2: a fresh terminal took 1 minute 47 seconds

I tested the skill in a fresh claude-deepseek terminal: OPEN TERMINAL AGENT using qodercli. By my clock it took 1 minute 47 seconds, so I asked it what took so long. Its transcript shows the window command returned in half a second. The rest was the agent convincing itself the window was really there: 12 commands, 11 round trips to the model, and two thinking steps of 19.4 and 16.6 seconds near the end.

A fresh claude-deepseek terminal after OPEN TERMINAL AGENT using qodercli. I write: 1min 47s, state what took you time on each step, be accurate and detailed. The agent starts by saying it has no timestamps for its own tool calls.
Step 2, about 8:02 PM ET. I ask what took 1 minute 47 seconds.

The agent couldn't account for the time, but Claude Code's own turn timer agrees with my clock: 107.9 seconds. About 9.7 of them passed before my prompt was logged, while the new session was still starting up, so 98.2 seconds is the fair number to compare.

Step 3: Claude Duet pitched the fastest check

I asked Claude Duet for the fastest way to confirm the terminal is open and in front. Its answer: give the window a unique title when you launch it, then make one call that reads the title of whatever window is in front. A match proves that exact window is in front, which a process check can't. It also flagged the risk that Windows can refuse to bring a new window forward, so the check should be able to say a window exists but isn't in front.

My Claude Duet chat. I say cutting steps is the critical factor for every capability in the workshop and ask for the fastest verify path. Claude Duet suggests launching the window with a unique title and the suppressApplicationTitle flag, then one PowerShell call that reads the foreground window's title, guesses about 1 to 2 seconds untimed, and flags that Windows may keep another app in front.
Step 3. Claude Duet's pitch: a unique window title, then one read of the front window.

Step 4: Codex red-teamed it

I asked Codex, on GPT-6.1-Sol at max effort, to red-team the skill and find a faster way to confirm the terminal opened and is in front. It moved the checks into one helper the agent runs once. The helper opens the window with a unique title, then checks the new process, its folder and that exact window together, and says whether the window is in front, behind or minimized. Codex also stopped the trigger firing when someone is only editing the skill, and left a tested way to roll the change back. Its checks: all 7 harnesses opened, one launch each, the helper alone taking 1.4 to 4.6 seconds.

OpenAI Codex 0.165.0 with the model changed to gpt-6.1-sol max. My prompt asks it to red-team the skill and find a faster way to verify the terminal is in front and opened, for a benchmark report on the site. Codex has read the claude-deepseek session and reports the qodercli open took 98.2 s against the 107 s I saw, with the launch about half a second and two thinking steps about 36 s.
Step 4, 8:11 PM ET. Codex on GPT-6.1-Sol at max effort reads the slow run before red-teaming the skill.

Step 5: 11 seconds, skill saved

Then I ran the same request in a fresh claude-deepseek terminal: 11.4 seconds, 2 commands, 3 round trips to the model, and the helper reported the window in front. The model wrote 546 tokens instead of 11,778. Same harness, same model, same target, about 8.6 times faster. The skill stays as rebuilt.

A fresh claude-deepseek terminal reads Settled, 11s. Its recap says it opened a qodercli terminal agent window in the workshop folder, confirmed running in the foreground, and that the harness's login and model readiness are untested.
Step 5, 8:42 PM ET. Settled in 11 seconds. The recap itself says login and model readiness weren't tested.

Skill lookup: the right skill first for 20 of 22 requests, up from 9

Before an agent can use one of my workshop's skills, it has to find the right one; there were 265 at the time. The old lookup matched keywords. On 22 everyday requests, like "come up with a clickable title and thumbnail for my next upload", it put the right skill first for 9, and for 5 it found nothing at all.

The lookup now asks a small embedding model, embeddinggemma-2, which compares what a request means instead of its exact words. It runs on the CPU, loads for one lookup and unloads, so it never holds the graphics card. On the same 22 requests it put the right skill first for 20. The two it still missed asked to write a new skill and to make a voiceover. Both lookups correctly found nothing for 2 off-topic requests, like "tell me a joke about cats".

The cost is time: 6.8 to 11.2 seconds per lookup, against a quarter to half a second for keywords. Exact trigger phrases like OPEN TERMINAL AGENT and exact skill names still go first and never load the model, and if the model is busy or fails, the lookup falls back to keywords.

Limits of this report

  • One run before and one after, on one PC. Model speed varies between runs, so 98 to 11 seconds is one measured pair, not an average.
  • The 7-harness check is one run of the helper alone per harness: no model reading the skill or replying.
  • The skill confirms the harness window opened and is in front; it doesn't test that the model inside is signed in and ready.
  • The transcripts are private logs on my PC; this page summarises them and shows my own screenshots.
  • The skill lookup test is one run of 22 requests, and the lookup's settings were chosen on those same requests, so new wording will likely score a little lower.

Follow the lab

New test reports and tier-list changes get announced in my Discord's #news channel. The full videos are on YouTube.

Receipts

9 items

DanManREAL · AI lab

Test receipt

AuditOct 28, 2026

claude-deepseek (Claude Code on deepseek-flash)

Step 2: open a Qoder CLI terminal, first skill
98.2 s · 12 commands8:00 PM ET; 11 round trips to the model. Claude Code's own timer read 107.9 s, my 1 minute 47 seconds, about 9.7 s of it before my prompt was logged, while the session was still starting up
Step 5: same request, rebuilt skill
11.4 s · 2 commands8:42 PM ET; 3 round trips to the model; the helper reported the new window in front. Claude Code's timer: 11.5 s
Tokens the model wrote, one open
11,778 → 546and it read 502,520 tokens before (457,600 of them cached) against 126,151 after (83,456 cached)
Where the 98 seconds went
launch 0.5 s · two thinking steps 36 sthe window command returned in 0.516 s; the agent's last two thinking steps, spent deciding whether its window evidence was enough, took 19.4 and 16.6 s
Step 1, no skill: open a Codex terminal
74.6 s · 18 commands7:51 PM ET; the agent then listed 11 steps, and cut them to the 3-step recipe that became the first skill
Step 4: red-team agent
Codex · GPT-6.1-Sol, max effortasked at 8:11 PM ET for a faster way to confirm the terminal opened and is in front
Rebuilt skill's checks
7/7 harnesses opened · 15/15 regressionsone launch per harness, helper only, 1.4 to 4.6 s each; plus a rollback tested on a copy
Skill lookup: right skill first, 22 requests
9/22 → 20/22October 27, 10:27 PM ET; keyword lookup against the embedding-model lookup on the same 22 everyday requests. Both correctly matched nothing on 2 off-topic requests
Skill lookup: time per lookup
0.24–0.52 s → 6.8–11.2 sthe model loads on the CPU for one lookup and unloads after; the graphics card stayed at 0 MiB. The PC was busy with other work during the test

Verdict

98 s → 11 s · 11 round trips → 3

Tier list A test of my own workshop skill with one agent, so it places no model on the tier list.

danmanreal.com/tests/open-terminal-agent-steps-reduced

What was tested

OPEN TERMINAL AGENT, my workshop skill for opening agent terminalsclaude-deepseek: Claude Code 2.1.312 running deepseek-flashClaude Duet, which pitched the fastest checkCodex CLI 0.165.0 (GPT-6.1-Sol, max effort) as the red-team agentWindows Terminal on WSL2 Ubuntudmr-skill-route, my workshop's skill finder, with the embeddinggemma-2 model on the CPU through dmr-small

Related

Independent testing. Sponsorships are always disclosed, and verdicts are never for sale.

Disagree? Bring your receipts

All reports

36 reports