Agent skill

Delivery Routing

by grandamenium in grandamenium/cortextos

Route research summaries to local markdown, Telegram, or Slack with approval gates and delivery-state updates.

MITAuto-check passedDocuments & Office

Install Delivery Routing

skills CLI
$ npx skills add grandamenium/cortextos --skill delivery-routing -a claude-code

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

GitHub CLI
$ gh skill install grandamenium/cortextos delivery-routing --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/grandamenium/cortextos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/community/agents/research-agent/.claude/skills/delivery-routing .claude/skills/delivery-routing && 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
delivery-routing
GitHub stars
101
Token cost
~1.5k tokens
SKILL.md length
419 words
Files
1
Skills in repo
55
Repo updated
First seen
Licence
MIT

At a glance

Route research summaries to local markdown, Telegram, or Slack with approval gates and delivery-state updates.

  • Works in 3 steps: Write the summary to… → Log: delivery_fallback… → Do not raise -- delivery failure is…
  • Tasks that involve Markdown
  • SKILL.md covers When to Use, Input, Output and Approval Gate, plus 5 more sections
  • Calls curl

What it does

Delivery Routing is an agent skill from grandamenium/cortextos. Route research summaries to local markdown, Telegram, or Slack with approval gates and delivery-state updates.

Its SKILL.md is about 1.5k 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 Documents & Office, covering Markdown. It works with Telegram and Slack. The licence is MIT.

When your agent uses it

  • Tasks that involve Markdown

Example prompts

  • “/delivery-routing”

Requirements

  • Python 3

Workflow steps

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

  1. Write the summary to research/output/YYYY-MM-DD/DELIVERY-FAILED-summary.md.
  2. Log: delivery_fallback path=research/output/YYYY-MM-DD/DELIVERY-FAILED-summary.md
  3. Do not raise -- delivery failure is non-fatal to the run.

What it can do on your machine

Read from SKILL.md and the folder at commit 6f93838. 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:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    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

Delivery Routing loads about 1.5k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 419 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 grandamenium/cortextos at commit 6f93838, republished under its MIT licence (© grandamenium). 419 words, ~1,493 tokens.

Download SKILL.mdSave it as .claude/skills/delivery-routing/SKILL.md (or your agent's skills folder).
name
delivery-routing
description
Route research summaries to local markdown, Telegram, or Slack with approval gates and delivery-state updates.

Delivery Routing

Send the run summary to the configured destination through cortextOS-safe delivery paths. Mark items as delivered only after successful delivery.


When to Use

After brief-generation writes the run summary.


Input

  • research/output/YYYY-MM-DD/summary.md
  • research/output/YYYY-MM-DD/signals-selected.json (needed to mark delivered_at on success)
  • config.json (delivery config)
  • research/db/signals.db (to mark delivered_at after successful delivery)

Output

  • Message sent to configured destination, OR approval request created through cortextOS approvals
  • delivered_at set on delivered items in research/db/signals.db
  • Delivery status appended to research/output/YYYY-MM-DD/run.log

Approval Gate

Always check research.delivery.requires_approval before sending externally. External destinations are telegram and slack. local_markdown and none do not leave the machine.

If true (default)

Create a cortextOS approval, write a local approval context file, notify the user, and stop. Do not send externally until the approval is granted.

Every approval must have a parent task. If this delivery was started by a cron or ad-hoc workflow and no task exists yet, create a run task first and mark it in_progress.

research/output/YYYY-MM-DD/PENDING-APPROVAL.md
markdown
# Delivery Pending Approval -- YYYY-MM-DD

Run complete. Summary ready but not sent (`research.delivery.requires_approval = true`).

**Approval:** Created through `cortextos bus create-approval`.

**Summary path:** research/output/YYYY-MM-DD/summary.md
**Signals selected:** N
**Top signals:**
1. [Title] (score: X.X)
2. [Title] (score: X.X)
3. [Title] (score: X.X)

Use the normal approval workflow:

bash
APPR_ID=$(cortextos bus create-approval \
  "Send research summary for YYYY-MM-DD" \
  external-comms \
  "Destination: ${DESTINATION}. Summary: research/output/YYYY-MM-DD/summary.md. Pending context: research/output/YYYY-MM-DD/PENDING-APPROVAL.md")
cortextos bus send-telegram "$CTX_TELEGRAM_CHAT_ID" \
  "Approval needed: research summary for YYYY-MM-DD is ready. Check dashboard approval ${APPR_ID}."
cortextos bus log-event action approval_created info \
  --meta "{\"approval_id\":\"${APPR_ID}\",\"destination\":\"${DESTINATION}\"}"

If this run has a parent task, block that task on the approval. If it was cron started and has no parent task, create one before requesting approval, then block that task on the approval ID.

Log: Delivery pending approval. Request at research/output/YYYY-MM-DD/PENDING-APPROVAL.md approval_id=$APPR_ID

If false

Send to configured destination automatically, then mark delivered_at.


Destinations

Telegram
bash
cortextos bus send-telegram "$CTX_TELEGRAM_CHAT_ID" "$MESSAGE"

Message format: run date, signals collected vs. selected, top 3-5 titles with scores, any source failures, path to full output folder.

Keep under 4,096 characters. If longer, split into two messages.

Show full SKILL.md (171 more words)Show less
Slack

Use Slack only when the workspace webhook is configured and approval policy allows external delivery.

bash
curl -s -X POST "${SLACK_WEBHOOK_URL}" \
  -H "Content-Type: application/json" \
  -d '{"text": "MESSAGE"}'
Local Markdown

Write research/output/YYYY-MM-DD/DELIVERED-summary.md as a copy of the summary. No external HTTP calls.

None

No delivery. Summary stays at research/output/YYYY-MM-DD/summary.md.


Message Content

Send only the summary -- not full brief text. The full briefs live on disk at research/output/YYYY-MM-DD/briefs/.

Minimum content:

  • Run date and time
  • Number of signals selected out of total collected
  • Top 3-5 signals: title, score
  • Any source failures from run.log
  • Path to full output folder

Error Handling

Retry up to 3 times with 5-minute intervals between attempts.

python
import time

def deliver_with_retry(send_fn, max_retries=3, delay_seconds=300):
    for attempt in range(1, max_retries + 1):
        try:
            send_fn()
            return True
        except Exception as e:
            log(f"delivery_failure attempt={attempt} detail={e}")
            if attempt < max_retries:
                time.sleep(delay_seconds)
    return False

If all 3 attempts fail:

  1. Write the summary to research/output/YYYY-MM-DD/DELIVERY-FAILED-summary.md.
  2. Log: delivery_fallback path=research/output/YYYY-MM-DD/DELIVERY-FAILED-summary.md
  3. Do not raise -- delivery failure is non-fatal to the run.

Config Schema

Read delivery settings from config.json:

json
{
  "research": {
    "delivery": {
      "destination": "local_markdown",
      "requires_approval": true,
      "summary_only": true
    }
  }
}

Supported destinations:

  • local_markdown
  • telegram
  • slack
  • none

Mark delivered_at (After Successful Delivery Only)

After the message sends successfully, call mark_delivered():

python
import sqlite3, datetime as dt, json

def mark_delivered(db_path, selected_json_path):
    with open(selected_json_path) as f:
        selected = json.load(f)
    conn = sqlite3.connect(db_path)
    now = dt.datetime.utcnow().isoformat()
    for item in selected:
        conn.execute(
            "UPDATE items SET delivered_at=? WHERE canonical_key=?",
            (now, item["canonical_key"])
        )
        conn.execute(
            """UPDATE daily_brief_items
               SET delivered=1, delivered_at=?
               WHERE item_id = (SELECT id FROM items WHERE canonical_key = ?)""",
            (now, item["canonical_key"])
        )
    conn.commit()
    conn.close()

This ensures items are only suppressed from future runs if delivery actually succeeded. If delivery failed, they remain eligible for the next run.

© grandamenium, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in community/agents/research-agent/.claude/skills/delivery-routing of grandamenium/cortextos.

Open the folder on GitHubat commit 6f93838

Compare with similar skills

Delivery Routing 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.

Delivery Routing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Delivery Routing this skillgrandamenium/cortextos101—~1.5kAutomated safety check: PassMIT
Im Adapter0xranx/golembot322—~1.4kAutomated safety check: PassMIT
Slack Docsslackapi/slack-skills-plugin147—~2.2kAutomated safety check: PassMIT
Slack Messagingslackapi/slack-skills-plugin147—~1.3kAutomated safety check: PassMIT
Creating Letta Code Channelsletta-ai/skills149—~1.1kAutomated safety check: PassMIT
Workflow AutomatorLeoYeAI/openclaw-master-skills2.2k—~4.7kAutomated safety check: PassMIT

Similar skills

  • Im Adapter

    0xranx/golembot

    Format responses for instant messaging platforms such as Lark, DingTalk, WeCom, Slack, and Telegram.

    322 GitHub stars~1.4k tokensUpdated 12 days ago
    Productivity & AutomationAuto-check passed
  • Slack Docs

    slackapi/slack-skills-plugin

    Official

    A skill your agent uses when answering a conceptual or how-to question about Slack platform features, or when asked to look up, fetch, or summarize a docs.slack.dev page, including a pasted…

    147 GitHub stars~2.2k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Slack Messaging

    slackapi/slack-skills-plugin

    Official

    A skill your agent uses when writing, drafting, scheduling, or improving a Slack message, announcement, or reply sent via the Slack MCP tools (slacksendmessage, slacksendmessagedraft…

    147 GitHub stars~1.3k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Builds and debugs Letta Code channels, including first-party channel adapters and dynamic user channel plugins under ~/.letta/channels.

    149 GitHub stars~1.1k tokensUpdated 9 days ago
    Writing & ContentAuto-check passed
  • Workflow Automator

    LeoYeAI/openclaw-master-skills

    Automate repeatable workflows with WhatsApp/Telegram notifications, Excel/CSV processing, browser automation, and flexible scheduling.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Telegram Post

    glebis/claude-skills

    Create, preview, and send formatted Telegram posts from draft markdown files.

    391 GitHub stars~1.4k tokensUpdated 3 days ago
    Productivity & AutomationAuto-check passed

More from grandamenium/cortextos

All 55 skills in this repo
  • Cortext Self Diagnosis

    grandamenium/cortextos

    Diagnose cortextOS itself when the framework misbehaves — an agent has gone silent or wedged, agents are crash-looping, Telegram or agent-to-agent messages are not arriving, crons did not fire, an…

    101 GitHub stars~3.7k tokensUpdated 18 days ago
    Auto-check passed
  • Activity Channel

    grandamenium/cortextos

    You have completed something significant and want the whole org — all agents and the user — to know about it.

    101 GitHub stars~624 tokensUpdated 18 days ago
    Auto-check passed
  • Agentcard Purchase

    grandamenium/cortextos

    You need to make a purchase on behalf of the user — buy a SaaS subscription, pay for an API, purchase a domain, or any transaction requiring a credit card.

    101 GitHub stars~1.1k tokensUpdated 18 days ago
    Auto-check passed
  • Claude To Codex Migration

    grandamenium/cortextos

    Migrate ANY cortextOS agent from the claude-code runtime to the live codex-app-server runtime.

    101 GitHub stars~12k tokensUpdated 18 days ago
    Auto-check: warnings
  • Bus Reference

    grandamenium/cortextos

    Complete cortextos bus CLI reference - all available commands with examples.

    101 GitHub stars~3.8k tokensUpdated 18 days ago
    Auto-check passed
  • Business News Monitor

    grandamenium/cortextos

    Daily cron-driven scan of news/forums/social in a domain to surface market shifts, new competitors, regulatory changes, and net-new opportunities.

    101 GitHub stars~1.3k tokensUpdated 18 days ago
    Auto-check passed

Works with

Questions about Delivery Routing

What does Delivery Routing do?

Route research summaries to local markdown, Telegram, or Slack with approval gates and delivery-state updates. Delivery Routing is an agent skill from grandamenium/cortextos. Route research summaries to local markdown, Telegram, or Slack with approval gates and delivery-state updates.

When should I use Delivery Routing?

Delivery Routing fits situations like: tasks that involve Markdown.

How do I install Delivery Routing in Claude Code?

Run `npx skills add grandamenium/cortextos --skill delivery-routing -a claude-code`. Or copy the skill folder (community/agents/research-agent/.claude/skills/delivery-routing in grandamenium/cortextos) into .claude/skills/delivery-routing in your project. Claude Code loads it when a task matches its description.

How do I install Delivery Routing in Codex?

Run `npx skills add grandamenium/cortextos --skill delivery-routing -a codex`. Or copy the skill folder (community/agents/research-agent/.claude/skills/delivery-routing in grandamenium/cortextos) into .agents/skills/delivery-routing in your project. Codex loads it when a task matches its description.

Can I use Delivery Routing 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 grandamenium/cortextos --skill delivery-routing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/delivery-routing, .gemini/skills/delivery-routing, .github/skills/delivery-routing and .opencode/skills/delivery-routing in your project.

What does Delivery Routing need to run?

Going by SKILL.md and its folder, Delivery Routing needs the command-line tools its instructions call (curl). Our summary lists: Python 3.

Does Delivery Routing access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Delivery Routing 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 Delivery Routing use?

Delivery Routing 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 Delivery Routing use?

About 1.5k tokens (SKILL.md is roughly 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 Delivery Routing?

Skills that share tags, products or a category with Delivery Routing: Im Adapter (0xranx/golembot, 322 stars), Slack Docs (slackapi/slack-skills-plugin, 147 stars), Slack Messaging (slackapi/slack-skills-plugin, 147 stars) and Creating Letta Code Channels (letta-ai/skills, 149 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Delivery Routing?

grandamenium (a GitHub user) maintains it in grandamenium/cortextos, which has 101 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on September 23, 2026.

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