agentmods.dev

gram: Skill for Claude Code

.agents/skills/gram-pubsub-python/SKILL.md

gram-pubsub-python is a skill for Claude Code, Codex from speakeasy-api/gram. It costs 253 tokens per session (4,163 once invoked), scanned A, original, AGPL-3.0.

A project-specific guide for building and running Google Cloud Pub/Sub stream subscribers in Python. Pub/Sub is Google's service for sending messages through topics to receiving applications called subscribers.

In plain words
What is it for?
Use it for Python Pub/Sub work in Gram, including subscriber changes involving pystreams, graminfra.pubsub, or the multi command.
Why use it?
It explains the Gram project's subscriber commands, supporting library, and asynchronous runtime so related code follows the existing Python and Go design.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing. Also seen: installed under .agents/ (shared by several agents).

This is speakeasy-api/gram's own configuration. It tells Claude Code and Codex how to work on gram itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gram configures →

not rated 277repo +2 changed 28d ago A scan 253 tokens AGPL-3.0
View source ↗ speakeasy-api/gram speakeasy.com
Reuse

Borrowing it

Nothing to install: this file belongs to speakeasy-api/gram. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/speakeasy-api/gram/main/.agents/skills/gram-pubsub-python/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/speakeasy-api/gram

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 gram-pubsub-python

README.md
[![agentmods](https://agentmods.dev/badge/skills/speakeasy-api/gram/gram-pubsub-python/github.svg)](https://agentmods.dev/skills/speakeasy-api/gram/gram-pubsub-python)
Your own site
<a href="https://agentmods.dev/skills/speakeasy-api/gram/gram-pubsub-python"><img src="https://agentmods.dev/badge/skills/speakeasy-api/gram/gram-pubsub-python/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gram-pubsub-python

Your own site · 80×15
<a href="https://agentmods.dev/skills/speakeasy-api/gram/gram-pubsub-python"><img src="https://agentmods.dev/badge/skills/speakeasy-api/gram/gram-pubsub-python.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 253 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00253 $0.04163
Opus 5.5 $0.00101 $0.01665
Sonnet 5.5 $0.00051 $0.00833
Haiku 4.5 $0.00025 $0.00416

Measured 28d ago against content hash 1187c20e5ea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gram-pubsub-python 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 28d 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.

.agents/skills/gram-pubsub-python/SKILL.md · 280 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 28d ago Changed · +2 tokens per session 1187c20e5ea9
  2. 2mo ago First seen · 280 lines · 251 tokens per session scan A 3174c09a41d9

Subscribe to this mod's changes

gram-pubsub-python is a skill published in the GitHub repository speakeasy-api/gram (277 stars, last pushed today), licensed AGPL-3.0. It adds 253 tokens to every session and 4,163 once invoked, about $0.0010 per session on Opus 5.5. 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 2026-08-30.

DevOps and cloudGoLanguagesTypeScriptagentsmcpopenapiserverless
Related

gram-pubsub-python compared with skills from other repositories

gram-pubsub-python next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gram-pubsub-pythonspeakeasy-api/gramSkill277todayAGPL-3.0A253Claude Code, Codex
pn-go-scaffoldingperniemann/pnCoreSkill05d agoMITA51Cursor
effect-v4ComposioHQ/composioSkill31kyesterdayMITA159Claude Code, Codex
typescriptgenkit-ai/genkitSkill6.6kyesterdayApache-2.0A20Claude Code, Codex
ax-go-genax-llm/axSkill3.0k3d agoApache-2.0A54Claude Code, Codex
ax-go-agentax-llm/axSkill3.0k3d agoApache-2.0A57Claude Code, Codex
ax-go-audioax-llm/axSkill3.0k3d agoApache-2.0A45Claude Code, Codex