Borrowing it
Nothing to install: this file belongs to jeremylongshore/claude-code-slack-channel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jeremylongshore/claude-code-slack-channel/main/CLAUDE.mdgit clone --depth 1 https://github.com/jeremylongshore/claude-code-slack-channelWrote 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/instructions/jeremylongshore/claude-code-slack-channel/claude-md)<a href="https://agentmods.dev/instructions/jeremylongshore/claude-code-slack-channel/claude-md"><img src="https://agentmods.dev/badge/instructions/jeremylongshore/claude-code-slack-channel/claude-md/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.
<a href="https://agentmods.dev/instructions/jeremylongshore/claude-code-slack-channel/claude-md"><img src="https://agentmods.dev/badge/instructions/jeremylongshore/claude-code-slack-channel/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.06246 | $0.06246 |
| Opus 5 | $0.03123 | $0.03123 |
| Sonnet 5 | $0.01249 | $0.01249 |
| Haiku 4.5 | $0.00625 | $0.00625 |
Grade C, and why
claude-code-slack-channel CLAUDE.md scanned grade C with 2 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 10d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
**Upgrade**: `AUDIT_HARNESS_VERSION=vX.Y.Z curl -sSL https://raw.githubusercontent.com/jeremylongshore/audit-harness/main/install.sh | bash`. Or run `/sync-testing-harness` from any session. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Upgrade**: `AUDIT_HARNESS_VERSION=vX.Y.Z curl -sSL https://raw.githubusercontent.com/jeremylongshore/audit-harness/main/install.sh | bash`. Or run `/sync-testing-harness` from any session. How it starts
The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
Slack channel for the Claude Code — two-way chat bridge via Socket Mode + MCP stdio.
AGENTS.mdis the cross-tool sibling of this file. Top-levelAGENTS.mdfollows the open agents.md spec and is the instruction surface read by non-Claude assistants (Codex CLI, Cursor, Cline, Gemini CLI, Copilot, etc.). ThisCLAUDE.mdis the Claude-Code-specific layer. When a fact in one (architecture, security model, gates) changes, update both — they must not drift.
Architecture
Bun/TypeScript, strict mode. ~17 production source files (LoC drifts every commit — run wc -l *.ts for current). The load-bearing core:
| File | ~LoC | Purpose |
|---|---|---|
server.ts |
3820 | Stateful runtime — Slack client bootstrap, MCP server, event handlers, file I/O |
lib.ts |
2552 | Pure functions — gate(), assertSendable(), assertOutboundAllowed(), session types, audit-receipt + idempotent-send helpers |
supervisor.ts |
1810 | SessionSupervisor — activate / deactivate / quiesce, idle reaper, quarantine (Epic 32), outbox drain (drainOutbox, ccsc-o7x) |
journal.ts |
1461 | Hash-chained audit log — JournalWriter, verifyJournal, redactor (Epic 30-A) |
policy.ts |
818 | Declarative policy engine — evaluate(), detectShadowing, checkMonotonicity (Epic 29) |
manifest.ts |
573 | Bot-manifest protocol — schema, publish-side validation, subset check (Epic 31) |
Supporting modules (epic-scoped; each file header carries its ccsc-* bead tag):
| File(s) | Purpose |
|---|---|
crypto.ts · audit-key-loader.ts · audit-key-cli.ts |
Ed25519 audit-event signing over RFC 8785 JCS + keypair load/CLI (journal v2) |
admin.ts · mute-store.ts · nonce-hitl.ts |
Operator admin command dispatcher, peer-bot mute store, HMAC-nonce cross-channel HITL approval |
policy-dispatch.ts |
Side-effect-free dispatcher routing a gated call through evaluate() to allow/deny/require |
peer-bot-rate-limit.ts |
Per-(channel, bot_id) sliding-window limit breaking A→B→A runaway loops |
stream-reply.ts |
Progressive Slack reply via chat.update |
acp-adapter.ts |
Agent Client Protocol (ACP) stdio boundary adapter |
slack-delivery.ts |
Slack-WebClient adapter (~738 LoC) for the crash-safe reply-delivery outbox (ccsc-o7x): findDelivered / post with the idempotency key stamped into message metadata. Kept a sibling of server.ts so it can be unit-tested against a faked client without triggering server module-load side effects; the idempotent-send logic itself lives in lib.ts (makeIdempotentSend, deliveryIdempotencyKey). |
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.
- 10d ago First seen · 340 lines · 6,246 tokens per session scan C 4900c3e3dec4
claude-code-slack-channel CLAUDE.md is an instructions file published in the GitHub repository jeremylongshore/claude-code-slack-channel (39 stars, last pushed today), licensed Apache-2.0. It adds 6,246 tokens to every session, about $0.0312 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.