New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Terminal Agent Improvement Loop

by nowledge-co in nowledge-co/con-terminal

Run a benchmark-driven improvement loop for Con's terminal agent.

MITAuto-check passed

Install Terminal Agent Improvement Loop

skills CLI
$ npx skills add nowledge-co/con-terminal --skill terminal-agent-improvement-loop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nowledge-co/con-terminal terminal-agent-improvement-loop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nowledge-co/con-terminal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/terminal-agent-improvement-loop .claude/skills/terminal-agent-improvement-loop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
terminal-agent-improvement-loop
GitHub stars
625
Token cost
~681 tokens
SKILL.md length
279 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Run a benchmark-driven improvement loop for Con's terminal agent.

  • Works in 8 steps: Choose the smallest operator profile… → Run the benchmark on an idle tab → Score the resulting run with the… → …
  • Iterating on pane awareness
  • SKILL.md covers Workflow and Rules
  • Calls python3

What it does

Terminal Agent Improvement Loop is an agent skill from nowledge-co/con-terminal. Run a benchmark-driven improvement loop for Con's terminal agent. Use when iterating on pane awareness, SSH/tmux behavior, coding-cli flows, benchmark scoring, or progress tracking across many runs.

Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with tmux and Python. The repository describes itself as: The Native Terminal Emulator with a builtin AI Harness. The licence is MIT.

When your agent uses it

  • Iterating on pane awareness
  • SSH/tmux behavior
  • Coding-cli flows
  • Benchmark scoring

Example prompts

  • “/terminal-agent-improvement-loop”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Choose the smallest operator profile that matches the problem.
  2. Run the benchmark on an idle tab
  3. Score the resulting run with the matching rubric
  4. Record one short summary, a few lessons, and a few next-focus bullets in the score record.
  5. Append the scorecard to the tracked improvement log
  6. Make one focused product change.
  7. Re-run the same operator profile.
  8. Generate a report when you need to inspect trend

What it can do on your machine

Read from SKILL.md and the folder at commit d3c8d80. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Terminal Agent Improvement Loop loads about 681 tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 279 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~681

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nowledge-co/con-terminal at commit d3c8d80, republished under its MIT licence (© nowledge-co). 279 words, ~681 tokens.

Download SKILL.mdSave it as .claude/skills/terminal-agent-improvement-loop/SKILL.md (or your agent's skills folder).
name
terminal-agent-improvement-loop
description
Run a benchmark-driven improvement loop for Con's terminal agent. Use when iterating on pane awareness, SSH/tmux behavior, coding-cli flows, benchmark scoring, or progress tracking across many runs.

Terminal Agent Improvement Loop

Use this skill when improving Con as a terminal-native agent, not just fixing a one-off bug.

Primary references:

Workflow

  1. Choose the smallest operator profile that matches the problem.
  2. Run the benchmark on an idle tab:
    • python3 benchmarks/terminal-agent/run.py --profile operator-local-codex-devloop --suite operator
    • for repeated clean iterations, prefer python3 benchmarks/terminal-agent/iterate.py ...
  3. Score the resulting run with the matching rubric:
    • python3 benchmarks/terminal-agent/score.py --profile ... --record ... --score ...
    • or ask the built-in agent to judge the raw record and transcript first: python3 benchmarks/terminal-agent/judge_llm.py --profile ... --record ... --socket /tmp/con.sock
    • then turn that judge artifact into a normal scorecard: python3 benchmarks/terminal-agent/score.py --profile ... --record ... --judge-file ...
  4. Record one short summary, a few lessons, and a few next-focus bullets in the score record.
  5. Append the scorecard to the tracked improvement log:
    • python3 benchmarks/terminal-agent/log_iteration.py --scorecard ... --change "..."
  6. Make one focused product change.
  7. Re-run the same operator profile.
  8. Generate a report when you need to inspect trend:
    • python3 benchmarks/terminal-agent/report.py

Rules

  • Use strict suites to protect the floor and operator suites to judge real workflows.
  • Prefer operator profiles that start a fresh conversation and have bounded step timeouts.
  • Prefer typed control-plane improvements over prompt-only fixes.
  • Do not overfit to a single benchmark phrase or one host layout.
  • Keep unknowns honest when the backend cannot prove more.
  • When benchmark infra changes, say whether the product improved or the measurement improved.
  • Keep iteration notes concise and comparable across runs.
  • Keep docs/impl/terminal-agent-improvement-log.md useful to a human reader; it should explain what changed, not just repeat the numeric score.
  • If you use the LLM judge, feed it the raw record and transcript, not only the generated report. The report is a summary, not primary evidence.

© nowledge-co, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/terminal-agent-improvement-loop of nowledge-co/con-terminal.

Open the folder on GitHubat commit d3c8d80

Compare with similar skills

Terminal Agent Improvement Loop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Terminal Agent Improvement Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Terminal Agent Improvement Loop this skillnowledge-co/con-terminal625—~681Automated safety check: PassMIT
Using Tmux For Interactive Commandsobra/superpowers-lab4303 repos~1.3kAutomated safety check: PassMIT
Git History Bug Auditben-manes/caffeine18k—~3.3kAutomated safety check: PassApache-2.0
Pypi ReleasealchemiststudiosDOTai/tunacode125—~2.2kAutomated safety check: PassMIT
Tt Sidebarstormzhang/token-tracker528—~440Automated safety check: PassMIT
Term CLIEliasOenal/term-cli103—~3.3kAutomated safety check: PassBSD-3-Clause-Clear

Similar skills

  • Using Tmux For Interactive Commands

    obra/superpowers-lab

    A skill your agent uses when you need to run interactive CLI tools (vim, git rebase -i, Python REPL, etc.) that require real-time input/output - provides tmux-based approach for controlling…

    430 GitHub starsUsed in 3 repos~1.3k tokens
    DevelopmentAuto-check passed

  • Git History Bug Audit

    ben-manes/caffeine

    Audits a module by walking its git history commit by commit, tracking unresolved issues forward, and reporting the ones that survive to HEAD as findings.

    18k GitHub stars~3.3k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Pypi Release

    alchemiststudiosDOTai/tunacode

    This skill should be used when releasing tunacode-cli to PyPI.

    125 GitHub stars~2.2k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

  • Tt Sidebar

    stormzhang/token-tracker

    Open a live Token Tracker sidebar for only the current Codex session in a right-side terminal split at one-third width.

    528 GitHub stars~440 tokensUpdated 4 days ago
    Auto-check passed

  • Term CLI

    EliasOenal/term-cli

    Controls interactive terminal sessions for running long-lived processes, servers, REPLs, debuggers, and TUI programs without blocking.

    103 GitHub stars~3.3k tokensUpdated 2 mo ago
    DatabasesAuto-check passed

  • Nerd Font Icon Lookup

    malob/nix-config

    Works around Claude Code filtering private-use Unicode so agents can read and write Nerd Font icons in Starship, tmux and prompt configs.

    463 GitHub stars~697 tokensUpdated 4 days ago
    DevelopmentAuto-check passed

More from nowledge-co/con-terminal

  • Con CLI E2E

    nowledge-co/con-terminal

    Validate Con's local socket control plane against a real running app session, and write/run con-test integration tests.

    625 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Changelog Release Notes

    nowledge-co/con-terminal

    Maintain Con's CHANGELOG.md and release notes. An agent skill from nowledge-co/con-terminal.

    625 GitHub stars~686 tokensUpdated today
    Auto-check passed

  • Release

    nowledge-co/con-terminal

    Run and verify Con beta, dev, and stable releases without publishing incomplete artifacts.

    625 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Terminal Agent Benchmark

    nowledge-co/con-terminal

    Run and maintain Con's terminal-agent benchmark against a live app session.

    625 GitHub stars~822 tokensUpdated today
    Auto-check passed

Works with

Questions about Terminal Agent Improvement Loop

What does Terminal Agent Improvement Loop do?

Run a benchmark-driven improvement loop for Con's terminal agent. Terminal Agent Improvement Loop is an agent skill from nowledge-co/con-terminal. Run a benchmark-driven improvement loop for Con's terminal agent.

When should I use Terminal Agent Improvement Loop?

Terminal Agent Improvement Loop fits situations like: iterating on pane awareness; SSH/tmux behavior; coding-cli flows; benchmark scoring.

How do I install Terminal Agent Improvement Loop in Claude Code?

Run `npx skills add nowledge-co/con-terminal --skill terminal-agent-improvement-loop -a claude-code`. Or copy the skill folder (skills/terminal-agent-improvement-loop in nowledge-co/con-terminal) into .claude/skills/terminal-agent-improvement-loop in your project. Claude Code loads it when a task matches its description.

How do I install Terminal Agent Improvement Loop in Codex?

Run `npx skills add nowledge-co/con-terminal --skill terminal-agent-improvement-loop -a codex`. Or copy the skill folder (skills/terminal-agent-improvement-loop in nowledge-co/con-terminal) into .agents/skills/terminal-agent-improvement-loop in your project. Codex loads it when a task matches its description.

Can I use Terminal Agent Improvement Loop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nowledge-co/con-terminal --skill terminal-agent-improvement-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/terminal-agent-improvement-loop, .gemini/skills/terminal-agent-improvement-loop, .github/skills/terminal-agent-improvement-loop and .opencode/skills/terminal-agent-improvement-loop in your project.

What does Terminal Agent Improvement Loop need to run?

Going by SKILL.md and its folder, Terminal Agent Improvement Loop needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Terminal Agent Improvement Loop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Terminal Agent Improvement Loop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Terminal Agent Improvement Loop use?

Terminal Agent Improvement Loop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Terminal Agent Improvement Loop use?

About 681 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Terminal Agent Improvement Loop?

Skills that share tags, products or a category with Terminal Agent Improvement Loop: Using Tmux For Interactive Commands (obra/superpowers-lab, 430 stars), Git History Bug Audit (ben-manes/caffeine, 18k stars), Pypi Release (alchemiststudiosDOTai/tunacode, 125 stars) and Tt Sidebar (stormzhang/token-tracker, 528 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Terminal Agent Improvement Loop?

nowledge-co (a GitHub organization) maintains it in nowledge-co/con-terminal, which has 625 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.

Source: nowledge-co/con-terminal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.