Front

What it does

When your agent uses it

• Tasks that involve Email management

Example prompts

• “/front”

Requirements

• Python 3

Workflow steps

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

1. 1Reads need no confirmation. Every write (reply, assign, tag) requires the exact-match --confirm string: run the command once without it…
2. 2Replies send real messages to real people: show the user the exact --body before confirming, and double-check the --conversation id and…
3. 3Front's conversation-update API replaces all tags, so tag first reads the conversation's current tags and merges the new ones in…
4. 4Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/front.py). Do not print, log, or transmit the token value.

What it can do on your machine

Read from SKILL.md and the folder at commit d6dc5d8. 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 script files (Python), which the agent can run.

  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

Front loads about 869 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 312 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~49

When it runs · the whole SKILL.md, loaded when a task matches

~869

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

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 Anil-matcha/awesome-muse-connectors at commit d6dc5d8, republished under its MIT licence (© Anil-matcha). 312 words, ~869 tokens.

name

front

description

Work with Front: list inboxes and conversations, reply to conversations, assign teammates, add tags. Writes need --confirm. Trigger phrases: front, front inbox, shared inbox, support inbox.

metadata.includeInPrompt

true

tagline

Read your Front shared inbox, and reply, assign teammates, and add tags on conversations (writes need --confirm).

catalog_auth

Front API token (per-user, Front Settings → API)

catalog_hosts

api2.frontapp.com

bin/front.py inboxes                        # list inboxes (name, address)
bin/front.py conversations --inbox inb_123  # recent conversations (subject, status)
bin/front.py teammates                      # teammates (id, name, email)

# writes: every one requires the exact --confirm string the CLI prints
bin/front.py reply --conversation cnv_123 --to customer@example.com --body "<p>Thanks for writing in.</p>"
bin/front.py reply --conversation cnv_123 --to customer@example.com --body "<p>Update:</p>" --subject "Re: billing question" --author-id tea_456
bin/front.py assign --conversation cnv_123 --teammate tea_456
bin/front.py assign --conversation cnv_123 --unassign
bin/front.py tag --conversation cnv_123 --tags tag_1,tag_2

© Anil-matcha, 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 1 other file in connectors/front of Anil-matcha/awesome-muse-connectors.

• SKILL.md
• bin/front.py

Open the folder on GitHubat commit d6dc5d8