signal-operations

A workflow for preparing and diagnosing Signal private or group messages through a local signal-cli bridge, which is a command-line connection to Signal.

In plain words
What is it for?
Checking Signal setup, verifying the bridge and recipient, preparing private or group messages, and managing approved outgoing messages.
Why use it?
Signal delivery depends on a trusted local bridge, account pairing, and strict recipient allowlists. The workflow can prepare an audited message without claiming it was sent when delivery is unavailable.

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/signal-operations
Any agent
npx skills add CodeInfinity1/Stram --skill signal-operations
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 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 $0.00032 $0.00501
Opus 5 $0.00016 $0.00251
Sonnet 5 $0.00006 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 2d ago against content hash b422e813e3d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

signal-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/signal-operations/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Signal Operations

Purpose

Represent Signal as a privacy-focused native channel contract. Stram catalogs Signal and can prepare audited outbox messages; actual account delivery requires a trusted local signal-cli bridge.

When To Use

Use when the user asks about Signal onboarding, Signal private messages, group Signal chats, local bridge requirements, or privacy-preserving channel choices.

Inputs And Evidence

  • Phone number, Signal account reference, or group ID.
  • channel_manifest for signal.
  • signal-cli binary availability from channel_doctor.
  • Allowlist and pairing state.
  • Prepared outbox envelope.

Tool Map

  • channel_manifest
  • channel_setup_requirements
  • channel_setup_status
  • channel_doctor
  • channel_message_prepare
  • channel_outbox
  • message-approval-policy

Workflow

  1. Read the signal manifest and setup requirements.
  2. Run channel_doctor to check whether signal-cli is available.
  3. Confirm the exact recipient or group ID and allowlist status.
  4. Prepare outbound messages through channel_message_prepare.
  5. If a trusted local bridge is not active, report that delivery is prepared but not sent.
  6. Keep Signal state and account pairing inside the trusted bridge boundary.

Native Implementation Boundaries

  • Stram must own any signal-cli bridge adapter it uses.
  • Do not install or call external reference Signal plugins as implementation.
  • Do not claim direct delivery until the native bridge returns a sent status.

Safety And Approval

  • Signal messages can be sensitive; never auto-send.
  • Do not store Signal private keys or pairing artifacts in skill files or setup JSON.
  • Use exact recipients, exact text, and explicit user approval.

Verification

  • channel_doctor should reveal binary/setup gaps.
  • channel_outbox proves prepared envelopes.
  • Direct send support remains blocked unless a native bridge is implemented and configured.

Failure Modes

  • Confusing prepared outbox with encrypted delivery.
  • Sending to a phone number that was not allowlisted.
  • Leaking Signal account metadata into unrelated memory records.

Read the full file on GitHub · 72 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 · 72 lines · 32 tokens per session scan A b422e813e3d9

Subscribe to this mod's changes

signal-operations is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 32 tokens to every session and 501 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.