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 HybridAIOne/hybridclaw --skill mailchimpgit clone --depth 1 https://github.com/HybridAIOne/hybridclawWrote 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/hybridaione/hybridclaw/mailchimp)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/mailchimp"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/mailchimp/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/hybridaione/hybridclaw/mailchimp"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/mailchimp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 36 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 285 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 140 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 283 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 300 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00034 | $0.03373 |
| Opus 5 | $0.00017 | $0.01687 |
| Sonnet 5 | $0.00007 | $0.00675 |
| Haiku 4.5 | $0.00003 | $0.00337 |
Grade A, and why
mailchimp 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 12d 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mailchimp
Use this skill for Mailchimp Marketing and Mailchimp Transactional work: audience/list inspection, subscriber lookup and controlled mutations, tags, merge fields, campaign draft operations, campaign content, scheduling/sending, campaign reports, automation and journey readouts, and Mandrill transactional message lookup or sends.
Default Workflow
- Start with
credential-checkwhen setup is uncertain. The helper emits gateway-resolved<env:...>and<secret:...>placeholders; it does not read runtime env or secret values itself. MissingMAILCHIMP_SERVER_PREFIX,MAILCHIMP_MARKETING_BASIC_AUTH,MAILCHIMP_MARKETING_OAUTH_TOKEN, orMANDRILL_API_KEYis surfaced by the gateway placeholder resolver or by a 401/403 upstream response. Do not runhybridclaw secret list,hybridclaw env list,grep, or local file inspection from the agent sandbox to decide whether Mailchimp values are configured; those checks can see the wrong runtime surface. For stored OAuth access tokens, useoauth metadata --auth oauthto retrieve the account-specific API endpoint and setMAILCHIMP_SERVER_PREFIXfrom the returned API endpoint host. - Use
mailchimp.cjsnoun/verb commands for live work. Normal commands send the helper-built request through the HybridClaw gateway/api/http/requestpath, so the gateway resolves<env:...>and<secret:...>placeholders server-side. Use--requestonly for dry-run/debug output; do not normally reconstruct or relayhttpRequestobjects with the built-inhttp_requesttool. - Treat
MAILCHIMP_MARKETING_BASIC_AUTH,MAILCHIMP_MARKETING_OAUTH_TOKEN, andMANDRILL_API_KEYas SecretRefs only. Never ask the operator to paste tokens into chat, never print rawAuthorizationheaders, and never include Mandrill keys in--body-json. - For audience writes, bulk subscriber plans, campaign draft/content writes,
campaign schedule/send, and Mandrill sends, first run
approval-plan, show the preview, and stop. After explicit operator approval for the named audience, campaign, or message target, run the approved helper command unchanged. - For 401 or 403, stop after the first failure and ask the operator to verify the token, user role, Transactional provisioning, and data-center prefix. Do not retry with broader permissions.
- For 429, report rate-limit guidance from
Retry-Afteror Mailchimp rate-limit headers when present. Do not start retry loops. - Minimize subscriber PII in summaries. Prefer subscriber hashes for lookup and archive/tag operations. Include email addresses only when required to create or update a member.
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.
- 12d ago First seen · 302 lines · 34 tokens per session scan A 74790eef4efa
mailchimp is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 3,373 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 2026-08-30.
Other skills, from other repositories
m3-notify
Poll the inbox for new notifications addressed to you.
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
dingtalk-message
A tool for sending DingTalk messages through either a group Webhook robot or an internal enterprise robot. DingTalk is a workplace messaging platform.
ima-skill
A unified IMA skill for managing personal notes and knowledge bases through the platform's APIs.
notes
A note-management skill for searching, reading, creating, and adding content to personal notes in IMA, a note and knowledge platform.
backfill-enumerate-drain
How to backfill a newly-added repo or team — the enumerate-then-drain loop, the single-event contract, and resume-safe todo discipline. Load this when handling a .added seed event with the planner on.