Process Inbox
telegramdesktop/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
Runs a construction company's back office by bridging Gmail, Drive and JobTread: routing email attachments to the PM system, checking project status and sending daily Telegram briefings.
$ npx skills add hewi333/Mom-n-Pop-Skills --skill construction-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hewi333/Mom-n-Pop-Skills construction-agent --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/hewi333/Mom-n-Pop-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/construction-agent .claude/skills/construction-agent && 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 "construction-agent" agent skill from https://github.com/hewi333/Mom-n-Pop-Skills/tree/main/skills/construction-agent into .claude/skills/construction-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "construction-agent", 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/hewi333/Mom-n-Pop-Skills/tree/main/skills/construction-agentType 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 hewi333/Mom-n-Pop-Skills --skill construction-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hewi333/Mom-n-Pop-Skills construction-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hewi333/Mom-n-Pop-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/construction-agent .agents/skills/construction-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "construction-agent" agent skill from https://github.com/hewi333/Mom-n-Pop-Skills/tree/main/skills/construction-agent into .agents/skills/construction-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "construction-agent", 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 hewi333/Mom-n-Pop-Skills --skill construction-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hewi333/Mom-n-Pop-Skills construction-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hewi333/Mom-n-Pop-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/construction-agent .cursor/skills/construction-agent && 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 "construction-agent" agent skill from https://github.com/hewi333/Mom-n-Pop-Skills/tree/main/skills/construction-agent into .cursor/skills/construction-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "construction-agent", 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/hewi333/Mom-n-Pop-Skills.git --path skills/construction-agent--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 hewi333/Mom-n-Pop-Skills --skill construction-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hewi333/Mom-n-Pop-Skills construction-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hewi333/Mom-n-Pop-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/construction-agent .gemini/skills/construction-agent && 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 "construction-agent" agent skill from https://github.com/hewi333/Mom-n-Pop-Skills/tree/main/skills/construction-agent into .gemini/skills/construction-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "construction-agent", 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 hewi333/Mom-n-Pop-Skills construction-agentInstalls 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 hewi333/Mom-n-Pop-Skills --skill construction-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hewi333/Mom-n-Pop-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/construction-agent .github/skills/construction-agent && 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 "construction-agent" agent skill from https://github.com/hewi333/Mom-n-Pop-Skills/tree/main/skills/construction-agent into .github/skills/construction-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "construction-agent", 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 hewi333/Mom-n-Pop-Skills --skill construction-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hewi333/Mom-n-Pop-Skills construction-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hewi333/Mom-n-Pop-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/construction-agent .opencode/skills/construction-agent && 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 "construction-agent" agent skill from https://github.com/hewi333/Mom-n-Pop-Skills/tree/main/skills/construction-agent into .opencode/skills/construction-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "construction-agent", 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.
construction-agentRuns a construction company's back office by bridging Gmail, Drive and JobTread: routing email attachments to the PM system, checking project status and sending daily Telegram briefings.
This reference implementation bridges three systems a construction or trades business already uses: Google Workspace email where leads and project documents arrive, a Drive folder where an existing script already dumps email attachments, and a project management system such as JobTread where those files and tasks need to end up. It targets an owner who gets documents by email, already has attachments landing in Drive, and does not want to manually download and re-upload everything into the PM system.
Most actions follow a draft-approve-execute pattern: the agent drafts a reply or upload, the owner approves it over a Telegram message, and only then does the agent execute. The one exception is the Drive-to-PM file routing itself, which runs autonomously on a cron every 15 minutes because it only moves files rather than deleting them, preserving the originals, though the owner still gets a notification of what was routed. Bundled Python scripts cover daily briefings, moving files from Drive into JobTread, Gmail access and the JobTread Pave API, with setup references for Google Workspace and the JobTread API.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 70a2273. It shows what the files ask for, not the result of running them.
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.
Ships 4 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
sshFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.jobtread.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
GOOGLE_CLIENT_SECRETJOBTREAD_GRANT_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Construction Business Agent loads about 2.3k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 1,030 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
All set in `~/.hermes/.env` (chmod 600):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.
The full file from hewi333/Mom-n-Pop-Skills at commit 70a2273, republished under its MIT licence (© hewi333). 1,030 words, ~2,325 tokens.
.claude/skills/construction-agent/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.A reference implementation of an AI agent that runs the back-office of a construction company. The agent orchestrates between three systems a construction business already uses:
The agent bridges the gap: it monitors Drive for new files, downloads them, uploads them to the PM system, and notifies the owner — all through text messages the owner already reads.
For who: A construction or trades business (general contractor, remodeler, specialty trade) where:
Every action follows the same philosophy as all Mom-n-Pop skills:
The exception is file routing (Drive → PM system), which runs autonomously on a cron because it's non-destructive (files are moved, not deleted; originals are preserved). The owner still gets a notification of what was routed.
This is the main pipeline. Many construction businesses already have a script that dumps email attachments to a Drive "raw inbox" folder. The agent completes the circuit:
Email arrives → existing script dumps attachment to Drive →
Agent polls Drive folder (every 15 min via cron) →
Downloads attachment locally (temp) →
Uploads to PM system via API →
Deletes local temp file →
Moves Drive file to "processed" folder →
Sends Telegram notification to ownerWhy the agent does this: The previous setup got files into Drive, but getting them from Drive into the PM system required manual download + upload. The agent automates that last mile.
~/.hermes/cache/google_token.json)gmail.readonly, gmail.send, drive.readonly, drive.file, calendar.readonlyreferences/google-workspace-setup.mdJobTread is a construction-specific PM system. The Pave API pattern applies to similar construction PM tools (Procore, Buildertrend, etc.) — adapt the query language to your specific system.
POST https://api.jobtread.com/pavereferences/jobtread-api-setup.mdAll set in ~/.hermes/.env (chmod 600):
# Google Workspace
GOOGLE_CLIENT_ID=your_client_id_here
GOOGLE_CLIENT_SECRET=your_client_secret_here
GOOGLE_MAILBOX=info@yourdomain.com
# JobTread (or your PM system)
JOBTREAD_GRANT_KEY=your_grant_key_here
JOBTREAD_ORG_ID=your_org_id_here
# Google Drive (for attachment pipeline)
GOOGLE_DRIVE_RAW_FOLDER_ID=your_raw_folder_id
GOOGLE_DRIVE_PROCESSED_FOLDER_ID=your_processed_folder_id| Name | Schedule | What |
|---|---|---|
| Daily Briefing | 0 8 * * * | Email summary, today's tasks, deadlines |
| Drive Poll | */15 * * * * | Check Drive for new attachments → upload to PM system |
| Weekly Summary | 0 9 * * 1 | Project progress, completed tasks, files processed |
| Script | Purpose | Requires |
|---|---|---|
scripts/google_mail.py | Gmail read/draft/send (Google API) | GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_MAILBOX |
scripts/jobtread_pave.py | JobTread Pave API client | JOBTREAD_GRANT_KEY, JOBTREAD_ORG_ID |
scripts/drive_to_jobtread.py | Email→Drive→PM pipeline | Google Drive + JobTread credentials |
scripts/daily_briefing.py | Morning briefing generator | All of the above |
If you use Procore, Buildertrend, CoConstruct, or another construction PM system instead of JobTread:
scripts/jobtread_pave.py with a client for your PM system's APIscripts/drive_to_jobtread.py to use your PM system's file upload endpointscripts/daily_briefing.py to query your PM system's task/project schemaThe pipeline pattern (Drive → download → upload → move → notify) stays the same.
PM system API keys can expire — JobTread grant keys expire after 3 months of inactivity. A daily briefing cron that queries the API keeps it active. If your PM system has similar expiration, keep it active with scheduled calls.
Google OAuth tokens refresh automatically but can fail if the refresh token is revoked (password change, admin revocation). Monitor for auth errors and re-run the authentication flow when needed.
Pave is NOT GraphQL — it's similar but different syntax. Inputs are passed after the $ symbol, and empty braces {} mean "return this field." Check the API explorer for your PM system before assuming GraphQL syntax works.
File routing is non-destructive — the pipeline moves Drive files to a "processed" folder rather than deleting them. This is intentional. If your pipeline deletes, add a confirmation step.
Headless VPS auth — the one-time Google OAuth flow needs a browser. Use SSH port forwarding (ssh -L 8080:localhost:8080) to complete the flow from your local machine, or run the auth on your local machine and copy the token file to the VPS.
Large file handling — construction documents (plans, permits) can be large. The Drive → PM upload uses a temp directory; ensure sufficient disk space. Clean up temp files after each run.
GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_MAILBOXgoogle_mail.py read --count 5 returns inboxJOBTREAD_GRANT_KEY, JOBTREAD_ORG_IDjobtread_pave.py projects returns project listdrive_to_jobtread.py --dry-run shows pending filesdrive_to_jobtread.py processes one file end-to-endreferences/google-workspace-setup.md — step-by-step Google OAuth setupreferences/jobtread-api-setup.md — JobTread Pave API guide© hewi333, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (scripts, references) in skills/construction-agent of hewi333/Mom-n-Pop-Skills.
Open the folder on GitHubat commit 70a2273
Construction Business Agent 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 |
|---|---|---|---|---|---|---|
| Construction Business Agent this skillhewi333/Mom-n-Pop-Skills | 122 | — | ~2.3k | Automated safety check: Notes | MIT | |
| Process Inboxtelegramdesktop/tdesktop | 33k | 2 repos | ~4.5k | Automated safety check: Pass | GPL-3.0 | |
| Continuetelegramdesktop/tdesktop | 33k | 2 repos | ~9.4k | Automated safety check: Pass | GPL-3.0 | |
| Google Workspaceyc-software/qm | 15k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Gws Gmail Readgoogleworkspace/cli | 31k | 1 repos | ~345 | Automated safety check: Pass | Apache-2.0 | |
| Gws Gmail Triagegoogleworkspace/cli | 31k | 1 repos | ~301 | Automated safety check: Pass | Apache-2.0 |
telegramdesktop/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
telegramdesktop/tdesktop
Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.
yc-software/qm
Read and act on the user's Gmail, Google Calendar, and Google Tasks through per-user OAuth.
googleworkspace/cli
Gmail: Read a message and extract its body or headers. An agent skill from googleworkspace/cli.
googleworkspace/cli
Gmail: Show unread inbox summary (sender, subject, date). An agent skill from googleworkspace/cli.
trpc-group/trpc-agent-go
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
hewi333/Mom-n-Pop-Skills
Runs a small service business lead from intake through estimate, owner approval over Telegram, Stripe payment link and customer email draft to payment tracking.
hewi333/Mom-n-Pop-Skills
Connects a small business to QuickBooks Online for customers, estimates, invoices and payments, using Intuit OAuth 2.0 with token refresh and sandbox or production setups.
hewi333/Mom-n-Pop-Skills
Procedures for changing the model, restarting and quietly tuning a live Hermes gateway that serves end-users on messaging platforms such as Telegram.
hewi333/Mom-n-Pop-Skills
A skill your agent uses when tracking customer interactions, managing leads, or building a lightweight CRM for small businesses without dedicated CRM software.
hewi333/Mom-n-Pop-Skills
A skill your agent uses when calculating service estimates for jobs.
hewi333/Mom-n-Pop-Skills
A skill your agent uses when integrating with Mailchimp for audience management, campaigns, and automation.
Works with
Categories
Runs a construction company's back office by bridging Gmail, Drive and JobTread: routing email attachments to the PM system, checking project status and sending daily Telegram briefings. This reference implementation bridges three systems a construction or trades business already uses: Google Workspace email where leads and project documents arrive, a Drive folder where an existing script already dumps email attachments, and a project management system such as JobTread where those files and tasks need to end up. It targets an owner who gets documents by email, already has attachments landing in Drive, and does not want to manually download and re-upload everything into the PM system.
Construction Business Agent fits situations like: routing a newly emailed project document from Drive into JobTread automatically; getting a daily Telegram briefing of today's tasks, deadlines and new emails; checking project status in the PM system without opening it directly; triaging what came into the inbox today for a construction business.
Run `npx skills add hewi333/Mom-n-Pop-Skills --skill construction-agent -a claude-code`. Or copy the skill folder (skills/construction-agent in hewi333/Mom-n-Pop-Skills) into .claude/skills/construction-agent in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hewi333/Mom-n-Pop-Skills --skill construction-agent -a codex`. Or copy the skill folder (skills/construction-agent in hewi333/Mom-n-Pop-Skills) into .agents/skills/construction-agent in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hewi333/Mom-n-Pop-Skills --skill construction-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/construction-agent, .gemini/skills/construction-agent, .github/skills/construction-agent and .opencode/skills/construction-agent in your project.
Going by SKILL.md and its folder, Construction Business Agent needs Python for the scripts in its folder, the command-line tools its instructions call (ssh) and credentials named GOOGLE_CLIENT_SECRET and JOBTREAD_GRANT_KEY. Our summary lists: Google Workspace (Gmail and Drive) access; A JobTread Pave API key; A Telegram bot for owner approvals and briefings; Python for the bundled scripts.
SKILL.md names 1 domain. In commands or code: api.jobtread.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. 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.
Construction Business Agent is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Construction Business Agent: Process Inbox (telegramdesktop/tdesktop, 33k stars), Continue (telegramdesktop/tdesktop, 33k stars), Google Workspace (yc-software/qm, 15k stars) and Gws Gmail Read (googleworkspace/cli, 31k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
hewi333 (a GitHub user) maintains it in hewi333/Mom-n-Pop-Skills, which has 122 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 11, 2026.
Source: hewi333/Mom-n-Pop-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.