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 skills add nevergoodstudy-hub/wechat-article-summarizer --skill capsule-crm-automationgit clone --depth 1 https://github.com/nevergoodstudy-hub/wechat-article-summarizerWrote 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/nevergoodstudy-hub/wechat-article-summarizer/capsule-crm-automation)<a href="https://agentmods.dev/skills/nevergoodstudy-hub/wechat-article-summarizer/capsule-crm-automation"><img src="https://agentmods.dev/badge/skills/nevergoodstudy-hub/wechat-article-summarizer/capsule-crm-automation/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/skills/nevergoodstudy-hub/wechat-article-summarizer/capsule-crm-automation"><img src="https://agentmods.dev/badge/skills/nevergoodstudy-hub/wechat-article-summarizer/capsule-crm-automation.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 | $0.00045 | $0.02000 |
| Opus 5.5 | $0.00018 | $0.00800 |
| Sonnet 5.5 | $0.00009 | $0.00400 |
| Haiku 4.5 | $0.00005 | $0.00200 |
Grade A, and why
Capsule CRM Automation 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 1mo 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.
This is a copy
100% identical to Capsule CRM Automation — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capsule CRM Automation
Manage your Capsule CRM -- create and update contacts, run powerful filter queries on parties/opportunities/cases, track tasks and projects, browse activity entries, and organize team relationships -- all through natural language commands.
Toolkit docs: composio.dev/toolkits/capsule_crm
Setup
- Add the Composio MCP server to your client configuration:
https://rube.app/mcp - Connect your Capsule CRM account when prompted (OAuth authentication).
- Start issuing natural language commands to manage your CRM.
Core Workflows
1. Run Structured Filter Queries
Query parties, opportunities, or cases (projects) with multiple filter conditions, operators, and sorting.
Tool: CAPSULE_CRM_RUN_FILTER_QUERY
Example prompt:
"Find all Capsule CRM contacts in California tagged as 'VIP' sorted by name"
Key parameters:
entity(required) -- One of:parties,opportunities,kasesfilter(required) -- Filter object with:conditions-- Array of conditions, each with:field-- Field name (e.g., "name", "email", "state", "country", "tag", "owner", "jobTitle", "addedOn")operator-- One of: "is", "is not", "starts with", "ends with", "contains", "is greater than", "is less than", "is after", "is before", "is older than", "is within last", "is within next"value-- Value to compare against
orderBy-- Array of sort objects withfieldanddirection("ascending"/"descending")
embed-- Additional data to include in responsepage/perPage-- Pagination (max 100 per page)
Important field notes:
- Address fields (
city,state,country,zip) are top-level, NOT nested under "address" - Country must be an ISO 3166-1 alpha-2 code (e.g., "US", "GB", "CA")
- Custom fields use
custom:{fieldId}format - Organization fields use
org.prefix (e.g.,org.name,org.tag)
2. List and Manage Contacts (Parties)
Retrieve all contacts with optional filtering by modification date and embedded related data.
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.
- 1mo ago First seen · 178 lines · 45 tokens per session scan A e9a83c371468
Capsule CRM Automation is a skill published in the GitHub repository nevergoodstudy-hub/wechat-article-summarizer (5 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 2,000 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to Capsule CRM Automation, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
resolution_playbook
How to choose one resolution action from a ticket and its customer history.
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
mintlify-api
Interact with the Mintlify REST API to manage deployments, trigger builds, and query documentation site metadata programmatically.
Envelope
Classify any incoming directive as Ship / Ask one focused question / Propose first. Forces a sharp decision instead of a multi-option survey to the principal. The default failure mode for agents is treating ship-work as ask-work (over-surveying) or treating propose-work as ship-work (rushing irreversible changes).…
nightly-ledger-capture
Discovers missing honesty, trust-decay, failure-mode, and decision-outcome entries from local evidence; stages judgment and permits direct mutation only after an executable oracle.
outbound-gate
Gate for any outbound message before it leaves: pull request or issue comment, DM, invite, post, email. Use before sending to check facts, tone, platform rules, registry status and AI-slop, and to block text that fails.