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.
npx agentmods add skills/jansenanalytics/claudex/draft-queuenpx skills add JansenAnalytics/claudex --skill draft-queuegit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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.
[](https://agentmods.dev/skills/jansenanalytics/claudex/draft-queue)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/draft-queue"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/draft-queue.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.00625 |
| Opus 5 | $0.00026 | $0.00313 |
| Sonnet 5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
draft-queue 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 today.
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.
What it actually says
Draft Queue Skill
Use when: you want to take an external action that requires the user's approval before executing.
Add a draft
node ${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/add-draft.cjs \
--type <type> \
--desc "description" \
--payload '<json>'
Types: telegram-message, shell-command, github-comment, github-pr-merge, file-write
Payloads by type
telegram-message
{ "chat_id": "<your-telegram-user-id>", "message": "text here" }
shell-command
{ "command": "echo hello", "cwd": "$HOME" }
github-comment
{ "repo": "JansenAnalytics/myrepo", "issue": 42, "body": "comment text" }
github-pr-merge
{ "repo": "JansenAnalytics/myrepo", "pr": 7, "method": "squash" }
file-write
{ "path": "/path/to/your/file.txt", "content": "file contents" }
Approve (when the user says "approve ID")
node ${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/approve.cjs <id>
Reject (when the user says "reject ID")
node ${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/reject.cjs <id>
List pending
node ${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/list-drafts.cjs
List all
node ${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/list-drafts.cjs --all
List by status
node ${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/list-drafts.cjs --status approved
Notes
- Drafts file:
${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/drafts.json(append-only) - Cron for expiry:
0 9 * * * /usr/bin/node ${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/expire-drafts.cjs >> ${DRAFT_QUEUE_HOME:-$HOME/projects/draft-queue}/draft-queue.log 2>&1 - add-draft.cjs prints the draft ID to stdout on success
- Default expiry: 24 hours. Override with
--expires 7detc.
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.
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.
- today First seen · 92 lines · 52 tokens per session scan A 4008998ccddd
draft-queue is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 625 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
morning-brief
Copy this template to your Claude Desktop scheduled-tasks directory.
ide-refactor
Safe refactoring with git-backed rollback. Verifies a clean working tree, performs the refactoring using LSP rename and code actions, runs tests, and offers to revert via git if anything breaks.
ide-type-mismatch-fix
Diagnose and fix TypeScript/language type errors using LSP diagnostics, hover, and code actions. For each type error, fetches the expected vs actual types, surfaces quickfix suggestions, and optionally applies them. Use when getDiagnostics shows type errors you want to resolve quickly.
ide-explore
Deep codebase exploration using IDE bridge LSP tools. Maps architecture, traces call chains, discovers entry points, and builds a mental model of unfamiliar code. Use when onboarding to a new codebase or understanding a module.
ide-api-deprecation-tracker
Find all @deprecated APIs in the workspace, count their callers, and extract migration guidance. Produces a prioritized report sorted by call count so you know which deprecations to tackle first.
ide-dead-code-hunter
Find unused exports, dead functions, and unreachable code across the workspace using LSP analysis. Cross-verifies detectUnusedCode with findReferences to eliminate false positives. Use to clean up technical debt or before a major refactor.