Agent skill

Debugging Tool Loops

by friday-platform in friday-platform/friday-studio

Loads when a session shows many tool calls (often the same name repeated) with no terminal text, no complete call, and either hits stopWhen: stepCountIs(...) (default 10) OR exhausts max output…

Custom licenceAuto-check passedDevelopment

Install Debugging Tool Loops

skills CLI
$ npx skills add friday-platform/friday-studio --skill debugging-tool-loops -a claude-code

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

GitHub CLI
$ gh skill install friday-platform/friday-studio debugging-tool-loops --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/friday-platform/friday-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/system/skills/debugging-tool-loops .claude/skills/debugging-tool-loops && 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
debugging-tool-loops
GitHub stars
104
Token cost
~777 tokens
SKILL.md length
333 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
Custom licence

At a glance

Loads when a session shows many tool calls (often the same name repeated) with no terminal text, no complete call, and either hits stopWhen: stepCountIs(...) (default 10) OR exhausts max output…

  • Works in 4 steps: Confirm the loop signature → Check the agent prompt's termination… → Check whether the agent has the right… → …
  • Tasks that involve Debugging
  • SKILL.md covers Diagnostic checklist, What NOT to do and Cross-references
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Debugging Tool Loops is an agent skill from friday-platform/friday-studio. Loads when a session shows many tool calls (often the same name repeated) with no terminal text, no complete call, and either hits stopWhen: stepCountIs(...) (default 10) OR exhausts max output tokens. The LLM is in a tool loop without producing a final message. Distinguish from debugging-empty-output — that's about contract exits being absent; this is about the LLM never deciding to stop. Required: the agent prompt needs an explicit termination criterion.

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging. The repository describes itself as: Agent Harness Platform — shareable workspaces, MCP tools, skills, memory, and cron/webhook automations. Self-hosted and transparent.

When your agent uses it

  • Tasks that involve Debugging

Example prompts

  • “Use the debugging-tool-loops skill to load when a session shows many tool calls (often the same name repeated) with no terminal text, no complete…”
  • “/debugging-tool-loops”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Confirm the loop signature
  2. Check the agent prompt's termination criterion
  3. Check whether the agent has the right terminal tool
  4. Bump max_steps only as a last resort

What it can do on your machine

Read from SKILL.md and the folder at commit fb3069a. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Debugging Tool Loops loads about 777 tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 333 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~122
When it runs · the whole SKILL.md, loaded when a task matches
~777

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 333 words (~777 tokens).

“Symptom: agent makes 8+ tool calls (often repeating searches with slight variations), eventually hits stepCountIs(10) cap or runs out of output tokens, ends with output: {response: ""} or empty complete args.”

— opening of SKILL.md by friday-platform, Custom licence
name
debugging-tool-loops

Read the full SKILL.md on GitHub

Files

Just SKILL.md in packages/system/skills/debugging-tool-loops of friday-platform/friday-studio.

Open the folder on GitHubat commit fb3069a

Compare with similar skills

Debugging Tool Loops 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.

Debugging Tool Loops compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Debugging Tool Loops this skillfriday-platform/friday-studio104—~777Automated safety check: PassCustom licence
Trellis Session Insightmindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.0
Native Data FetchingCherryHQ/cherry-studio-app4k6 repos~2.9kAutomated safety check: NotesMIT
Aoti Debugpytorch/pytorch104k1 repos~1.7kAutomated safety check: PassCustom licence
Herdr Throwaway Reproductionherdrdev/herdr43k—~2.4kAutomated safety check: PassApache-2.0
Systematic Debuggingultralisp/ultralisp25851 repos~2.4kAutomated safety check: PassNone

Similar skills

  • Trellis Session Insight

    mindfold-ai/Trellis

    Reach into past AI conversation history through the trellis mem CLI.

    15k GitHub starsUsed in 4 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Native Data Fetching

    CherryHQ/cherry-studio-app

    A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

    4k GitHub starsUsed in 6 repos~2.9k tokens
    DevelopmentAuto-check: notes
  • Aoti Debug

    pytorch/pytorch

    Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.

    104k GitHub starsUsed in 1 repo~1.7k tokens
    DevelopmentAuto-check passed
  • Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.

    43k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Systematic Debugging

    ultralisp/ultralisp

    A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    258 GitHub starsUsed in 51 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.

    23k GitHub stars~2.5k tokensUpdated 3 days ago
    DevelopmentAuto-check: notes

More from friday-platform/friday-studio

All 20 skills in this repo
  • Authoring Skills

    friday-platform/friday-studio

    Authors new agent skills that follow the Anthropic + agentskills.io specification.

    104 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Friday CLI

    friday-platform/friday-studio

    Interacts with a running Friday daemon via CLI and HTTP — lists/creates/modifies workspaces, triggers signals, watches sessions, publishes skills and agents.

    104 GitHub stars~4.3k tokensUpdated 1 mo ago
    Auto-check: notes
  • Workspace API

    friday-platform/friday-studio

    Create, list, update, delete, and clean up workspaces via the daemon HTTP API at $FRIDAYDURL.

    104 GitHub stars~9.3k tokensUpdated 1 mo ago
    Auto-check: notes
  • Writing Workspace Signals

    friday-platform/friday-studio

    Authors Friday workspace signals with correct provider configs, payload schemas, and runtime wiring.

    104 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Composing Emails

    friday-platform/friday-studio

    General styling and tone guidelines for composing HTML emails.

    104 GitHub stars~648 tokensUpdated 1 mo ago
    Auto-check passed
  • Repairing Workspaces Agents

    friday-platform/friday-studio

    Repairs and upgrades existing Friday workspaces, jobs, user agents, and generated agents to current runtime contracts.

    104 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Debugging Tool Loops

What does Debugging Tool Loops do?

Loads when a session shows many tool calls (often the same name repeated) with no terminal text, no complete call, and either hits stopWhen: stepCountIs(...) (default 10) OR exhausts max output…. Debugging Tool Loops is an agent skill from friday-platform/friday-studio.) (default 10) OR exhausts max output tokens.

When should I use Debugging Tool Loops?

Debugging Tool Loops fits situations like: tasks that involve Debugging.

How do I install Debugging Tool Loops in Claude Code?

Run `npx skills add friday-platform/friday-studio --skill debugging-tool-loops -a claude-code`. Or copy the skill folder (packages/system/skills/debugging-tool-loops in friday-platform/friday-studio) into .claude/skills/debugging-tool-loops in your project. Claude Code loads it when a task matches its description.

How do I install Debugging Tool Loops in Codex?

Run `npx skills add friday-platform/friday-studio --skill debugging-tool-loops -a codex`. Or copy the skill folder (packages/system/skills/debugging-tool-loops in friday-platform/friday-studio) into .agents/skills/debugging-tool-loops in your project. Codex loads it when a task matches its description.

Can I use Debugging Tool Loops 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 friday-platform/friday-studio --skill debugging-tool-loops -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/debugging-tool-loops, .gemini/skills/debugging-tool-loops, .github/skills/debugging-tool-loops and .opencode/skills/debugging-tool-loops in your project.

What does Debugging Tool Loops need to run?

SKILL.md names no scripts, command-line tools or credentials: Debugging Tool Loops is instructions for the agent only.

Does Debugging Tool Loops 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 Debugging Tool Loops 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 Debugging Tool Loops use?

Debugging Tool Loops has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Debugging Tool Loops use?

About 777 tokens (SKILL.md is roughly 3.1k 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 Debugging Tool Loops?

Skills that share tags, products or a category with Debugging Tool Loops: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Aoti Debug (pytorch/pytorch, 104k stars) and Herdr Throwaway Reproduction (herdrdev/herdr, 43k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Debugging Tool Loops?

friday-platform (a GitHub organization) maintains it in friday-platform/friday-studio, which has 104 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on September 5, 2026.

Source: friday-platform/friday-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.