channel-gateway-operations

A shared workflow for adding and operating several chat channels through Stram's native gateway tools.

In plain words
What is it for?
Onboarding communication channels, routing incoming events, preparing outgoing messages, checking whether direct sending is allowed, and handling quiet-room context.
Why use it?
Different messaging services need different setup checks and delivery rules. A common workflow keeps onboarding, routing, outbound approvals, context handling, and bot-loop prevention consistent.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/codeinfinity1/stram/channel-gateway-operations
Any agent
npx skills add CodeInfinity1/Stram --skill channel-gateway-operations
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00724
Opus 5 $0.00023 $0.00362
Sonnet 5 $0.00009 $0.00145
Haiku 4.5 $0.00005 $0.00072

Measured 2d ago against content hash 782eeb095fde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

channel-gateway-operations scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/communications/channel-gateway-operations/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Channel Gateway Operations

Purpose

Operate channels as native Stram transport surfaces. This skill turns native Gateway patterns into Stram-owned catalog, setup, policy, outbox, and interaction-harness workflows.

When To Use

Use when the task involves multiple channels, channel onboarding, gateway manifests, inbound event routing, outbound delivery, quiet room context, bot-loop suppression, or deciding whether a channel can send directly.

Inputs And Evidence

  • channel_id, conversation_id, conversation type, sender ID, message ID, mention state, and bot-authored flags.
  • Channel catalog or manifest output.
  • Setup status, missing environment variables, allowlists, and group policy.
  • Outbox item, send result, or inbound stimulus record.

Tool Map

  • channel_catalog
  • channel_manifest
  • channel_setup_requirements
  • channel_setup_status
  • channel_doctor
  • channel_integration_smoke
  • channel_listener_status
  • channel_webhook_ingest
  • channel_action_prepare
  • channel_message_prepare
  • channel_message_send
  • channel_outbox
  • activity_ingest
  • cognitive_interaction_review

Workflow

  1. Start with channel_catalog or channel_manifest for the exact channel.
  2. Inspect setup requirements and status before assuming direct send support.
  3. Run channel_integration_smoke for non-sending readiness evidence.
  4. Preserve structured metadata for inbound events; do not infer routing from message text alone.
  5. Apply channel policy: allowlist, pairing, mention, ambient room, bot-loop, and approval boundaries.
  6. Route accepted inbound messages as channel stimuli into the normal interaction harness.
  7. For outbound work, prepare an outbox envelope first unless a direct send is explicitly approved and configured.
  8. Report the exact delivery status: prepared, blocked, failed, dry run, or sent.

Native Implementation Boundaries

  • Use only Stram Gateway tools and owned adapters.
  • Do not import external reference Gateway code, external skill catalog plugins, or external channel packages as the skill implementation.
  • If a channel is cataloged but direct runtime support is missing, say that clearly and use prepared outbox or setup planning.

Read the full file on GitHub · 82 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 82 lines · 46 tokens per session scan A 782eeb095fde

Subscribe to this mod's changes

channel-gateway-operations is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 23d ago), licensed MIT. It adds 46 tokens to every session and 724 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.