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.
Explicitly preview or record rough Agent Harness ideas, requirements, bugs, and inbox notes without accepting scope or implementing it.
Install Intake
$ npx skills add 0xenzyme/agent-harness --skill intake -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install 0xenzyme/agent-harness intake --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/0xenzyme/agent-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/agent-harness/skills/intake .claude/skills/intake && 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 "intake" agent skill from https://github.com/0xenzyme/agent-harness/tree/main/plugins/agent-harness/skills/intake into .claude/skills/intake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intake", 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/0xenzyme/agent-harness/tree/main/plugins/agent-harness/skills/intakeType 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 0xenzyme/agent-harness --skill intake -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install 0xenzyme/agent-harness intake --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/0xenzyme/agent-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/agent-harness/skills/intake .agents/skills/intake && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "intake" agent skill from https://github.com/0xenzyme/agent-harness/tree/main/plugins/agent-harness/skills/intake into .agents/skills/intake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intake", 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 0xenzyme/agent-harness --skill intake -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install 0xenzyme/agent-harness intake --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/0xenzyme/agent-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/agent-harness/skills/intake .cursor/skills/intake && 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 "intake" agent skill from https://github.com/0xenzyme/agent-harness/tree/main/plugins/agent-harness/skills/intake into .cursor/skills/intake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intake", 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/0xenzyme/agent-harness.git --path plugins/agent-harness/skills/intake--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 0xenzyme/agent-harness --skill intake -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install 0xenzyme/agent-harness intake --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/0xenzyme/agent-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/agent-harness/skills/intake .gemini/skills/intake && 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 "intake" agent skill from https://github.com/0xenzyme/agent-harness/tree/main/plugins/agent-harness/skills/intake into .gemini/skills/intake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intake", 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 0xenzyme/agent-harness intakeInstalls 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 0xenzyme/agent-harness --skill intake -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/0xenzyme/agent-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/agent-harness/skills/intake .github/skills/intake && 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 "intake" agent skill from https://github.com/0xenzyme/agent-harness/tree/main/plugins/agent-harness/skills/intake into .github/skills/intake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intake", 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 0xenzyme/agent-harness --skill intake -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install 0xenzyme/agent-harness intake --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/0xenzyme/agent-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/agent-harness/skills/intake .opencode/skills/intake && 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 "intake" agent skill from https://github.com/0xenzyme/agent-harness/tree/main/plugins/agent-harness/skills/intake into .opencode/skills/intake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "intake", 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
intake- GitHub stars
- 107
- Token cost
- ~435 tokens
- SKILL.md length
- 179 words
- Files
- 3 (incl. references)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Explicitly preview or record rough Agent Harness ideas, requirements, bugs, and inbox notes without accepting scope or implementing it.
- Works in 5 steps: Read repo instructions and inspect the… → Preserve the raw idea, detect… → Preview first → …
- Tasks that involve Email management
- Calls node
What it does
Intake is an agent skill from 0xenzyme/agent-harness. Explicitly preview or record rough Agent Harness ideas, requirements, bugs, and inbox notes without accepting scope or implementing it. / 显式收集未确认事项，不执行。
Its SKILL.md is about 440 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/capture-promotion.md`).
It sits in Productivity & Automation, covering Email management. The repository describes itself as: Adapter-driven control plane for coding-agent work: tasks, goals, run DAGs, gates, verification, and state sync. The licence is MIT.
When your agent uses it
- Tasks that involve Email management
Example prompts
- “/intake”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read repo instructions and inspect the configured Goal-index and idea-inbox
- Preserve the raw idea, detect duplicates/dependencies, and propose a concise
- Preview first
- Record only with explicit authority
- When an idea inbox is configured, --record appends the candidate there and
What it can do on your machine
Read from SKILL.md and the folder at commit 098b96d. 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:
node
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
Intake loads about 435 tokens when it runs, and up to ~593 if it reads all its reference files. Until then it costs about 40 tokens; SKILL.md has 179 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from 0xenzyme/agent-harness at commit 098b96d, republished under its MIT licence (© 0xenzyme). 179 words, ~435 tokens.
Download SKILL.mdSave it as
.claude/skills/intake/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- intake
- description
- Explicitly preview or record rough Agent Harness ideas, requirements, bugs, and inbox notes without accepting scope or implementing it. / 显式收集未确认事项，不执行。
Harness Intake
Use intake for rough, unaccepted work. Preview is read-only; recording requires an explicit user request.
The current user instruction and project instructions take precedence over this skill. This skill supplies routing and safety boundaries; it does not add an approval requirement beyond the boundaries stated below.
Read Capture And Promotion before recording or promoting an intake candidate.
- Read repo instructions and inspect the configured Goal-index and idea-inbox paths.
- Preserve the raw idea, detect duplicates/dependencies, and propose a concise title, priority, section, acceptance hint, and likely spec need.
- Preview first:
node <plugin-root>/scripts/agent-harness.mjs intake idea --cwd <project> --idea "<idea>" --json- Record only with explicit authority:
node <plugin-root>/scripts/agent-harness.mjs intake idea --cwd <project> --idea "<idea>" --record --priority P2 --section Next- When an idea inbox is configured,
--recordappends the candidate there and leaves the accepted Goal index unchanged. Without an idea inbox, refuse unsupported table writes without changing the file. Do not promote a candidate to accepted scope, create Spec/Goal/Run artifacts, or implement it. An accepted ordinary change returns to the current host directly and may use bounded postflight sync for this already recorded Task; durable accepted work usesharness:executebefore execution only when its tier boundary applies.
© 0xenzyme, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in plugins/agent-harness/skills/intake of 0xenzyme/agent-harness.
- SKILL.md
- agents/openai.yaml
- references/capture-promotion.md
Open the folder on GitHubat commit 098b96d
Compare with similar skills
Intake 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 |
|---|---|---|---|---|---|---|
| Intake this skill0xenzyme/agent-harness | 107 | — | ~435 | Automated safety check: Pass | 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 | |
| Garden Inboxpaperclipai/paperclip | 99k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Career-Ops Gmail Lead Plugincareer-ops-hq/career-ops | 74k | — | ~233 | Automated safety check: Notes | MIT | |
| Skill CompassEvol-ai/SkillCompass | 216 | 1 repos | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Continue
telegramdesktop/tdesktop
Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.
Garden Inbox
paperclipai/paperclip
Scan a Paperclip user's Mine inbox, classify reversible archive candidates, request checkbox confirmation, and archive only accepted selections.
Career-Ops Gmail Lead Plugin
career-ops-hq/career-ops
Pulls job leads from a Gmail label into the career-ops pipeline, extracting job URLs from DMARC-passing emails and de-duplicating against existing leads.
Skill Compass
Evol-ai/SkillCompass
Evaluate skill quality, find the weakest dimension, and apply directed improvements.
Atomicmail
Atomic-Mail/atomic-mail-agentic
Read and write email through the Atomic Mail from an AI agent.
More from 0xenzyme/agent-harness
Execute
0xenzyme/agent-harness
Execute accepted long-running controller or durable Harness work, or postflight-sync already tracked work; ordinary clear changes use the current host directly.
Orient
0xenzyme/agent-harness
Inspect durable Agent Harness state and recommend the next public entry without mutation.
Init
0xenzyme/agent-harness
Explicitly audit, initialize, import, or repair Agent Harness setup and config migration; not for ordinary status, intake, or product implementation.
Related
Categories
Questions about Intake
What does Intake do?
Explicitly preview or record rough Agent Harness ideas, requirements, bugs, and inbox notes without accepting scope or implementing it. Intake is an agent skill from 0xenzyme/agent-harness. Explicitly preview or record rough Agent Harness ideas, requirements, bugs, and inbox notes without accepting scope or implementing it.
When should I use Intake?
Intake fits situations like: tasks that involve Email management.
How do I install Intake in Claude Code?
Run `npx skills add 0xenzyme/agent-harness --skill intake -a claude-code`. Or copy the skill folder (plugins/agent-harness/skills/intake in 0xenzyme/agent-harness) into .claude/skills/intake in your project. Claude Code loads it when a task matches its description.
How do I install Intake in Codex?
Run `npx skills add 0xenzyme/agent-harness --skill intake -a codex`. Or copy the skill folder (plugins/agent-harness/skills/intake in 0xenzyme/agent-harness) into .agents/skills/intake in your project. Codex loads it when a task matches its description.
Can I use Intake 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 0xenzyme/agent-harness --skill intake -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/intake, .gemini/skills/intake, .github/skills/intake and .opencode/skills/intake in your project.
What does Intake need to run?
Going by SKILL.md and its folder, Intake needs the command-line tools its instructions call (node).
Does Intake 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 Intake 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 Intake use?
Intake 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 Intake use?
About 435 tokens (SKILL.md is roughly 1.7k 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 158 tokens, read only when the agent opens those files.
What are the alternatives to Intake?
Skills that share tags, products or a category with Intake: Process Inbox (telegramdesktop/tdesktop, 33k stars), Continue (telegramdesktop/tdesktop, 33k stars), Garden Inbox (paperclipai/paperclip, 99k stars) and Career-Ops Gmail Lead Plugin (career-ops-hq/career-ops, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Intake?
0xenzyme (a GitHub user) maintains it in 0xenzyme/agent-harness, which has 107 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.
Source: 0xenzyme/agent-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.