comms-blast

comms-blast is a skill for Claude Code, Codex from Rohit-ATS/Airlock. It costs 40 tokens per session (1,696 once invoked), scanned A, original, MIT.

A safety guide for sending outbound messages to many people. It covers consent, exclusions, quiet hours, sender reputation, and removing duplicate recipients.

In plain words
What is it for?
Planning or reviewing bulk email changes, checking recipient counts, documenting exclusions, and enforcing safe sending rules.
Why use it?
It helps prevent accidental messages, repeated apologies to one person, unwanted contact, and other costly sending mistakes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/rohit-ats/airlock/comms-blast
Any agent
npx skills add Rohit-ATS/Airlock --skill comms-blast
Clone the repo
git clone --depth 1 https://github.com/Rohit-ATS/Airlock

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for comms-blast

README.md
[![agentmods](https://agentmods.dev/badge/skills/rohit-ats/airlock/comms-blast.svg)](https://agentmods.dev/skills/rohit-ats/airlock/comms-blast)
Your own site
<a href="https://agentmods.dev/skills/rohit-ats/airlock/comms-blast"><img src="https://agentmods.dev/badge/skills/rohit-ats/airlock/comms-blast.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,696 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 5.1 $0.00040 $0.01696
Opus 5 $0.00020 $0.00848
Sonnet 5 $0.00008 $0.00339
Haiku 4.5 $0.00004 $0.00170

Measured 5d ago against content hash dbd376c75a9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

comms-blast 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 5d 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/comms-blast/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comms blast

There is no unsend. An email that has been accepted by a receiving mail server is gone in a way a database row never is: it is on someone's phone, at 6am, and no amount of access to your own systems retrieves it.

A COMMS_BLAST change always carries a SCOPE certificate, and the exclusion list is the part that matters. Anyone can produce a list of recipients. The evidence that the send is safe is the list of people you deliberately did not write to, and why.


1. The audience is people, not addresses

Deduplicate by person, then by address, in that order. The failure otherwise is mundane and awful: one customer with three addresses on the account receives the apology three times, which reads as a second incident.

-- count what the policy ceiling actually measures
SELECT count(DISTINCT user_id)  AS people,
       count(DISTINCT lower(trim(email))) AS addresses
  FROM audience;

Report both. If addresses materially exceeds people, say so — it means the send is larger than the incident.

Normalise before comparing: lowercase, trim, and treat Gmail dots and +tags as the same mailbox for deduplication purposes only. Never rewrite a stored address to a normalised form; normalise for comparison and send to what the customer gave you.


2. Suppression is not optional and not one list

Four separate exclusions. Check each, count each, report each.

Exclusion Why Consequence of getting it wrong
Global unsubscribe They asked you to stop Unlawful under PECR/CAN-SPAM; also the reason they unsubscribed
Topic-level unsubscribe They opted out of this category Same, and harder to defend because you had the preference
Hard bounces in the last 30 days The mailbox does not exist Damages the sending domain's reputation for every other message
Spam complaints They marked you as spam Repeat sends to complainers is the fastest route to a blocklist

Plus one that is easy to forget and worst to get wrong:

Read the full file on GitHub · 173 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. 5d ago First seen · 173 lines · 40 tokens per session scan A dbd376c75a9b

Subscribe to this mod's changes

comms-blast is a skill published in the GitHub repository Rohit-ATS/Airlock (1 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,696 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.

Related

Other skills, from other repositories

reweave-operator

Operate a Reweave self-healing web-data fleet — run pipelines, triage structural-drift incidents, review repair proposals, and manage the human approval workflow. Use whenever a monitored source is broken, a heal is pending, or the operator asks about pipeline health or impact.

vnmoorthy/reweave · 62 tokens

resonate-server-postgres

Run the Resonate protocol inside Postgres itself using resonate-pg — one SQL file of stored procedures, with no server process at all. Covers installing the schema, the pgcron timer dependency and its silent-failure mode, reaching the protocol through resonaterpc, starting workflows with resonate.invoke, the…

resonatehq/resonate-skills · 112 tokens

prisma-schema-conventions

Data modeling conventions for Prisma + PostgreSQL in multi-tenant systems — workspace isolation, numeric criticality, idempotent recurrence, document versioning by lineage and decoupled audit via a queue in Postgres itself. Use whenever creating or changing schema.prisma, designing new entities, planning migrations or…

JoaoEquer/Oficina · 76 tokens

postgres-patterns

Provides PostgreSQL patterns for query optimization, schema design, indexing strategies, RLS, and security. Use when working with PostgreSQL SQL files or when the user mentions PostgreSQL, Postgres, pgvector, Supabase, or database optimization.

tranhieutt/software_development_department · 53 tokens

postgres-patterns

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Quick reference for common patterns, index types, data types, and anti-pattern detection. Based on Supabase best practices.

mturac/everything-openai-codex · 45 tokens

agent-harness-fault-injection

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

sickn33/agentic-awesome-skills · 34 tokens