Agentacct Workflow
mikehasa/agentacct
A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced.
Install Fake Model Provider Faults
$ npx skills add different-ai/openwork --skill fake-model-faults -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install different-ai/openwork fake-model-faults --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/fake-model-faults .claude/skills/fake-model-faults && rm -rf skills-srcUse ~/.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/
Install the "fake-model-faults" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/fake-model-faults into .claude/skills/fake-model-faults/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fake-model-faults", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/different-ai/openwork/tree/dev/.opencode/skills/fake-model-faultsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add different-ai/openwork --skill fake-model-faults -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install different-ai/openwork fake-model-faults --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/fake-model-faults .agents/skills/fake-model-faults && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fake-model-faults" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/fake-model-faults into .agents/skills/fake-model-faults/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fake-model-faults", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add different-ai/openwork --skill fake-model-faults -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install different-ai/openwork fake-model-faults --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/fake-model-faults .cursor/skills/fake-model-faults && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fake-model-faults" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/fake-model-faults into .cursor/skills/fake-model-faults/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fake-model-faults", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/different-ai/openwork.git --path .opencode/skills/fake-model-faults--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add different-ai/openwork --skill fake-model-faults -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install different-ai/openwork fake-model-faults --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/fake-model-faults .gemini/skills/fake-model-faults && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fake-model-faults" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/fake-model-faults into .gemini/skills/fake-model-faults/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fake-model-faults", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install different-ai/openwork fake-model-faultsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add different-ai/openwork --skill fake-model-faults -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/fake-model-faults .github/skills/fake-model-faults && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fake-model-faults" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/fake-model-faults into .github/skills/fake-model-faults/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fake-model-faults", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add different-ai/openwork --skill fake-model-faults -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install different-ai/openwork fake-model-faults --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/fake-model-faults .opencode/skills/fake-model-faults && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fake-model-faults" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/fake-model-faults into .opencode/skills/fake-model-faults/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fake-model-faults", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
fake-model-faults- GitHub stars
- 24k
- Token cost
- ~642 tokens
- SKILL.md length
- 192 words
- Files
- 3 (incl. scripts)
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced.
- Reproducing a model provider error or retry state without a real outage
- SKILL.md covers Set up, What each model does and Clean up
- Runs Python and JavaScript scripts from its folder; calls node and python3
- Designing messages for rate limit, auth or billing failures
What it does
Errors from a model provider come from the engine, the opencode sidecar, not from the app window, so browser-level network throttling cannot reproduce them. This skill points test providers at deliberate failures instead. It starts a local fault server on 127.0.0.1:55600 (the port is changeable) and runs `fault-providers.py add`, which backs up `runtime.sqlite` and adds three fault providers.
Each fault model produces one engine error: a refused connection, an unresolvable `.invalid` host, a socket reset (all with retries), a reset in the middle of a reply, a request that never answers, and HTTP 429, 500, 503, 401 and 402 responses with a JSON error body, plus an `ok` model for checking the pipeline. A DNS timeout and the OpenWork Cloud unavailable banner need a real network cut, such as turning Wi-Fi off for about 40 seconds, and the agent should ask first because it drops VPNs too. Cleanup removes the providers and stops the fault server.
When your agent uses it
- Reproducing a model provider error or retry state without a real outage
- Designing messages for rate limit, auth or billing failures
- Testing how the desktop app handles a stalled or cut model stream
Example prompts
- “Set up the fault providers and show me what the app displays on a 429.”
- “Reproduce the connection refused error with retries and capture a screenshot.”
- “Clean up the fault providers and stop the fault server.”
Requirements
- Node.js and Python 3, to run the bundled scripts
- The OpenWork desktop app with its local runtime
What it can do on your machine
Read from SKILL.md and the folder at commit 4ccc9e9. 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
Ships 2 files in scripts/ (Python and JavaScript), which the agent can run.
Shell commands in SKILL.md call:
nodepython3
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
Fake Model Provider Faults loads about 642 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 192 words of instructions outside code blocks.
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); the scripts in this folder 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 192 words (~642 tokens).
“Real provider errors come from the engine (the opencode sidecar), not from the window, so CDP network throttling cannot produce them. This skill points test providers at failures instead.”
- name
- fake-model-faults
Files
SKILL.md and 2 other files (scripts) in .opencode/skills/fake-model-faults of different-ai/openwork.
- SKILL.md
- scripts/fault-providers.py
- scripts/fault-server.mjs
Open the folder on GitHubat commit 4ccc9e9
Compare with similar skills
Fake Model Provider Faults 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fake Model Provider Faults this skilldifferent-ai/openwork | 24k | — | ~642 | Automated safety check: Pass | Custom licence | |
| Agentacct Workflowmikehasa/agentacct | 766 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Pipensx Bug Report Triagei3sey/pipensx | 221 | — | ~1.5k | Automated safety check: Notes | GPL-3.0 | |
| Sage Wiki Integratexoai/sage-wiki | 622 | — | ~861 | Automated safety check: Pass | MIT | |
| Antigravity SDK End-to-End Testingomnigent-ai/omnigent | 11k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Diagnoseipea/geobr | 959 | — | ~1.5k | Automated safety check: Pass | None |
Similar skills
Pipensx Bug Report Triage
i3sey/pipensx
Decodes QR-code bug report photos and screenshots from the pipensx app into a log, then triages crashes and update, download or install failures.
Sage Wiki Integrate
xoai/sage-wiki
Pipeline skill that wires sage-wiki into an existing project — detects language, installs the client, runs a smoke test, and reports.
Antigravity SDK End-to-End Testing
omnigent-ai/omnigent
Spins up a local Omnigent server and exercises the Antigravity (Gemini) SDK harness end to end: building agents, running real turns, smoke tests and bug-bashing.
Diagnose
ipea/geobr
Root-cause a failing or wrong geobr call with a disciplined check-the-environment-first loop instead of guessing.
Playwright Screen Recording
liaohch3/claude-tap
Records headless Playwright sessions as .webm videos to show a bug fix working or to give pull request reviewers visual evidence.
More from different-ai/openwork
All 33 skills in this repoOpenWork Desktop CDP Driver
different-ai/openwork
Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.
OpenWork Model Alias Manager
different-ai/openwork
Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models.
Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
OpenWork Electron Browser Automation
different-ai/openwork
Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.
Daytona Sandbox Operations
different-ai/openwork
Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests.
Daytona Seeded Cloud Demo
different-ai/openwork
Spins up a persistent OpenWork Cloud Den demo on a Daytona sandbox, seeds it with Acme Robotics data and returns shareable URLs and login details.
Related
Works with
Categories
Questions about Fake Model Provider Faults
What does Fake Model Provider Faults do?
Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced. Errors from a model provider come from the engine, the opencode sidecar, not from the app window, so browser-level network throttling cannot reproduce them. This skill points test providers at deliberate failures instead.
When should I use Fake Model Provider Faults?
Fake Model Provider Faults fits situations like: reproducing a model provider error or retry state without a real outage; designing messages for rate limit, auth or billing failures; testing how the desktop app handles a stalled or cut model stream.
How do I install Fake Model Provider Faults in Claude Code?
Run `npx skills add different-ai/openwork --skill fake-model-faults -a claude-code`. Or copy the skill folder (.opencode/skills/fake-model-faults in different-ai/openwork) into .claude/skills/fake-model-faults in your project. Claude Code loads it when a task matches its description.
How do I install Fake Model Provider Faults in Codex?
Run `npx skills add different-ai/openwork --skill fake-model-faults -a codex`. Or copy the skill folder (.opencode/skills/fake-model-faults in different-ai/openwork) into .agents/skills/fake-model-faults in your project. Codex loads it when a task matches its description.
Can I use Fake Model Provider Faults 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 different-ai/openwork --skill fake-model-faults -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fake-model-faults, .gemini/skills/fake-model-faults, .github/skills/fake-model-faults and .opencode/skills/fake-model-faults in your project.
What does Fake Model Provider Faults need to run?
Going by SKILL.md and its folder, Fake Model Provider Faults needs Python and JavaScript for the scripts in its folder and the command-line tools its instructions call (node and python3). Our summary lists: Node.js and Python 3, to run the bundled scripts; The OpenWork desktop app with its local runtime.
Does Fake Model Provider Faults 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 Fake Model Provider Faults 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Fake Model Provider Faults use?
Fake Model Provider Faults 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 Fake Model Provider Faults use?
About 642 tokens (SKILL.md is roughly 2.6k 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 Fake Model Provider Faults?
Skills that share tags, products or a category with Fake Model Provider Faults: Agentacct Workflow (mikehasa/agentacct, 766 stars), Pipensx Bug Report Triage (i3sey/pipensx, 221 stars), Sage Wiki Integrate (xoai/sage-wiki, 622 stars) and Antigravity SDK End-to-End Testing (omnigent-ai/omnigent, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Fake Model Provider Faults?
different-ai (a GitHub organization) maintains it in different-ai/openwork, which has 23,967 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 9, 2026.
Source: different-ai/openwork on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.