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/sanztheo/claude-intercom/skillnpx skills add sanztheo/claude-intercom --skill skillgit clone --depth 1 https://github.com/sanztheo/claude-intercomWrote 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/sanztheo/claude-intercom/skill)<a href="https://agentmods.dev/skills/sanztheo/claude-intercom/skill"><img src="https://agentmods.dev/badge/skills/sanztheo/claude-intercom/skill.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 | $0.00042 | $0.00639 |
| Opus 5 | $0.00021 | $0.00319 |
| Sonnet 5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
intercom 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intercom — Inter-Agent Communication
Purpose
Coordinate with other Claude Code instances working in parallel. Avoid file conflicts, duplicate work, and wasted effort by communicating proactively.
MANDATORY — On Every Task Start
Before doing ANY work, run these two calls:
mcp__intercom__who()→ discover who else is active on this projectmcp__intercom__peek()→ check if anyone sent you a message
If other agents are active, consider sending a brief message about what you're about to work on.
When to Communicate (Proactively)
Send a message (mcp__intercom__send) when:
| Situation | Example message |
|---|---|
| Starting work on a file | "Je commence à modifier src/auth/middleware.ts" |
| About to create a PR or push | "Je vais push sur feature/auth, heads up" |
| About to create a git worktree | "Je crée un worktree pour feature/billing" |
| Finished a task that unblocks others | "Auth middleware terminé et mergé, vous pouvez pull" |
| Found a bug or issue affecting others | "Attention: la migration DB 042 est cassée, ne pas merger" |
| Need information from another agent | "Qui gère le rate limiter ? J'ai besoin de contexte" |
When to Check Messages
Call mcp__intercom__peek():
- At task start (mandatory)
- Before modifying shared files (package.json, schema, configs)
- Before git operations (push, merge, rebase)
- Periodically during long tasks (every ~10 tool calls)
- Before claiming work is done
How to Reply
When you receive a message:
- If it asks a question →
mcp__intercom__reply(message_id, "your answer") - If it's informational →
mcp__intercom__ack(message_id)after reading - If it warns about a conflict → adjust your work accordingly, then reply
Scope
who(scope="project")→ agents on the same project (default)who(scope="all")→ all agents everywheresend(to="all", ...)→ broadcasts to same-project agentssend(to="x7k2", ...)→ direct message to a specific agent (works cross-project)
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.
- 4d ago First seen · 65 lines · 42 tokens per session scan A 50a861a73503
intercom is a skill published in the GitHub repository sanztheo/claude-intercom (2 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 639 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 2026-08-31.
Other skills, from other repositories
Copywriter
Copywriter delivers distinctive creative work grounded in audience, constraints, taste, iteration, and execution quality.
statsmodels
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use…
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
colab-finetuning
Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
rust-system-calls
Guides using bunsys for system calls and file I/O in Rust. Use when implementing file operations, opening fds, or any syscall path instead of std::fs or libc.