allowlist

allowlist is a skill for Claude Code from 2naive/claude-telegram-topics. It costs 70 tokens per session (513 once invoked), scanned A, original, Apache-2.0.

A setup skill that adds a plugin to Claude Code’s approved channel list, which controls whether inbound messages from connected channels can reach sessions.

In plain words
What is it for?
Use it when channel messages do not arrive, when setup reports that a plugin is not allowlisted, or when configuring channel access.
Why use it?
Without approval, outbound channel tools may work while incoming messages are silently unavailable. It also preserves existing managed settings and allowlist entries when updating them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the telegram-topics plugin — 3 skills, 4 hooks, 1 MCP server shipped together

Good fit Use it when channel messages do not arrive, when setup reports that a plugin is not allowlisted, or when configuring channel access.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add 2naive/claude-telegram-topics
Claude Code
/plugin install telegram-topics

Made for: Claude Code.

Or install telegram-topics, the plugin that ships this one along with the rest of its 3 skills, 4 hooks, 1 MCP server.

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 allowlist

README.md
[![agentmods](https://agentmods.dev/badge/skills/2naive/claude-telegram-topics/allowlist.svg)](https://agentmods.dev/skills/2naive/claude-telegram-topics/allowlist)
Your own site
<a href="https://agentmods.dev/skills/2naive/claude-telegram-topics/allowlist"><img src="https://agentmods.dev/badge/skills/2naive/claude-telegram-topics/allowlist.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 513 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 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 $0.00070 $0.00513
Opus 5 $0.00035 $0.00257
Sonnet 5 $0.00014 $0.00103
Haiku 4.5 $0.00007 $0.00051

Measured 6d ago against content hash 9f612a7af072, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

allowlist 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 6d 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/allowlist/SKILL.md · 53 lines

What it actually says

Allowlist the channel

--channels wires a channel ONLY for plugins on the approved-channels allowlist; anything else is silently loaded as a plain MCP plugin — outbound tools work, inbound never arrives. This skill approves the plugin in machine-level managed settings. Run:

bun run --cwd "${CLAUDE_PLUGIN_ROOT}" allowlist

(If ${CLAUDE_PLUGIN_ROOT} is not substituted, the plugin root is the installed plugin directory, e.g. ~/.claude/plugins/cache/claude-telegram-topics/telegram-topics/<version>.)

What it does, verbatim from its output:

  • already allowlisted — nothing to change; done.
  • Windows — writes C:\Program Files\ClaudeCode\managed-settings.json; if not elevated it raises one UAC prompt the user must approve at the machine.
  • macOS / Linux — writes the managed-settings path or, on permission denied, prints the exact sudo command for the user to run themselves.
  • The write is merge-safe (existing managed-settings keys and allowlist entries are preserved) and also carries the official Telegram plugin's entry, because a custom allowedChannelPlugins REPLACES the default Anthropic allowlist.

After a successful write, tell the user to restart their Claude Code sessions — the allowlist is read at session start.

No-admin alternative

Without machine admin rights the channel can still run via the development flag, which bypasses the allowlist:

claude --permission-mode auto --dangerously-load-development-channels plugin:telegram-topics@claude-telegram-topics

Trade-off: an interactive "local development" confirmation gates every start — fine for hand-started sessions, unusable for hands-off remote relaunch/autostart. Mention it when the user cannot (or does not want to) approve the admin write.

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. 6d ago First seen · 53 lines · 70 tokens per session scan A 9f612a7af072

Subscribe to this mod's changes

allowlist is a skill published in the GitHub repository 2naive/claude-telegram-topics (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 70 tokens to every session and 513 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 2026-08-31.