slack-drafts

A way to prepare Slack messages in the user's own Slack composer for review. Slack is a team messaging service, and these drafts are not posted automatically.

In plain words
What is it for?
Use it to draft a reply, prepare a message for a channel, or write into a specific Slack conversation or thread.
Why use it?
It saves the user from composing the message manually while leaving them in control of the final wording and sending.

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/yc-software/qm/slack-drafts
Any agent
npx skills add yc-software/qm --skill slack-drafts
Clone the repo
git clone --depth 1 https://github.com/yc-software/qm

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 644 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 $0.00038 $0.00644
Opus 5 $0.00019 $0.00322
Sonnet 5 $0.00008 $0.00129
Haiku 4.5 $0.00004 $0.00064

Measured 3d ago against content hash e819a883fef7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slack-drafts 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/slack_drafts.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-seed/slack-drafts/SKILL.md · 47 lines

What it actually says

Slack drafts

Use this skill when the user wants a Slack message prepared for them to review and send themselves: "draft a reply to X", "prep a message for #general", "write that up as a Slack draft". The draft lands in their own Slack composer, attributed to them, targeted at the conversation you choose — nothing is posted.

This is an OAuth connector. The resolved user's Slack user token lives on your computer as $VAULT_TOKEN_SLACK_COM. Do not ask the user for a token, log it, or use another principal's. If the variable is empty or Slack returns 401/403, the user either has not connected Slack or connected before this permission existed — tell them to (re)connect it through the product OAuth flow.

Use the bundled helper for every draft — it owns destination resolution, rich-text block construction, and the required draft envelope:

python3 skills/slack-drafts/scripts/slack_drafts.py create --to '#general' --text 'hello'
python3 skills/slack-drafts/scripts/slack_drafts.py create --to '@jane' --text-file body.txt
python3 skills/slack-drafts/scripts/slack_drafts.py create --to C0123ABCDEF --thread-ts 1712345678.000100 --text '...'
python3 skills/slack-drafts/scripts/slack_drafts.py resolve --to '#general'
  • --to takes a channel/IM ID (C…/G…/D…), a user ID (U…/W…), #channel-name, or @name (matched against username, display name, real name, or email; ambiguous matches are refused — fall back to a user ID).
  • Text is plain; URLs become clickable links. Write it exactly as the user would send it — it goes out under their name, in their voice, once they hit send.
  • --thread-ts targets the draft at a thread reply instead of the channel composer.
  • Drafts are create-only through this API: you cannot list, edit, or delete a draft once made. To revise, tell the user to discard the old draft in Slack and create a fresh one. Never work around this by posting messages — drafting means the user sends.
  • Opening a brand-new DM needs the im:write scope; tokens connected before that scope existed can only draft into conversations that already exist. On a missing_scope error, tell the user to reconnect Slack.
  • Slack keeps at most one draft per composer: a second draft into the same channel or thread fails with attached_draft_exists. Tell the user to send or discard the existing draft, then retry.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 47 lines · 38 tokens per session scan A e819a883fef7

Subscribe to this mod's changes

slack-drafts is a skill published in the GitHub repository yc-software/qm (14,428 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 644 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 2026-08-30.

Related

Other skills, from other repositories

building-pydantic-ai-agents

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…

pydantic/pydantic-ai · 85 tokens

complete-partial-pr

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

pydantic/pydantic-ai · 55 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

address-feedback

Find and address unresolved PR review comments for the current branch, then continue the canonical push, reply, reaction, and resolution workflow.

pydantic/pydantic-ai · 29 tokens

agent-initialization

Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.

Prism-Shadow/penguin-harness · 30 tokens

agent-mode

Unified tool for managing agent LLM modes (add, remove, update, list, switch).

PhyAgentOS/PhyAgentOS-core · 22 tokens