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 mathematic-inc/earl --skill create-templategit clone --depth 1 https://github.com/mathematic-inc/earlWrote 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/mathematic-inc/earl/create-template)<a href="https://agentmods.dev/skills/mathematic-inc/earl/create-template"><img src="https://agentmods.dev/badge/skills/mathematic-inc/earl/create-template/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/mathematic-inc/earl/create-template"><img src="https://agentmods.dev/badge/skills/mathematic-inc/earl/create-template.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 234 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 Prompt Injection · line 68 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Rogue Agent · line 108 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.02568 |
| Opus 5.5 | $0.00018 | $0.01027 |
| Sonnet 5.5 | $0.00009 | $0.00514 |
| Haiku 4.5 | $0.00005 | $0.00257 |
Grade A, and why
create-template 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 2mo 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Template
Creates an Earl HCL template file for a specific service and protocol. Each template defines the commands, parameters, authentication, and protocol shape for one provider.
Process
- Discover — understand what service and command to build
- Infer protocol — map the user's description to one of Earl's 5 protocols
- Load reference — read the protocol reference for HCL shapes and patterns
- Write template — create the HCL file
- Review — show the user the complete template before running it
- Validate — run
earl templates validate - Secrets — print checklist for the human to set secrets
- Verify — run a test
earl call
Phase 1: Discover Intent
If the request doesn't name a provider, command, and protocol, ask one question:
"What service do you want to call, and what should the command do? For example: 'Call the GitHub API to create an issue' or 'Query my PostgreSQL database for user records'."
Check for pre-built templates first
Earl ships with 26 ready-made provider templates. If the user names a known service, check whether it is already imported before offering to import it:
earl templates list
Check the list carefully:
- If the specific command needed is already present (e.g.
github.create_issueappears in the list), skip the import and go directly to Phase 7 to set any missing secrets. - If the provider is imported but the specific command is not in the list (e.g.
githubcommands appear but notgithub.create_issue), skip the import and proceed to custom template authoring (phases 2–6) to add the missing command to the existing file. - If the provider is not imported at all, offer to import the pre-built template:
# Available: github, stripe, slack, notion, openai, anthropic, recall_ai, discord, gitlab, jira, linear,
# pagerduty, twilio, sendgrid, cloudflare, vercel, render, shopify, hubspot,
# mailchimp, datadog, sentry, airtable, auth0, supabase, resend
earl templates import https://raw.githubusercontent.com/mathematic-inc/earl/main/examples/<provider>.hcl
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.
- 2mo ago First seen · 274 lines · 45 tokens per session scan A 8017aa8d9912
create-template is a skill published in the GitHub repository mathematic-inc/earl (113 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,568 once invoked, about $0.0002 per session on Opus 5.5. 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.
create-template compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-templatemathematic-inc/earl | Skill | 113 | 4d ago | Apache-2.0 | A | 45 | Claude Code, Codex |
| api-design-patternsbobmatnyc/claude-mpm | Skill | 158 | 2mo ago | none | A | 29 | Claude Code |
| api-designasgarovf/locusai | Skill | 23 | 8mo ago | MIT | A | 37 | Claude Code |
| goericrisco/rsc-harness | Skill | 555 | 4d ago | MIT | A | 86 | Claude Code, Codex |
| mcp2cliknowsuchagency/mcp2cli | Skill | 2.4k | 5d ago | MIT | B | 126 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 555 | 4d ago | MIT | A | 105 | Claude Code, Codex |
| lapLap-Platform/LAP | Skill | 347 | 13d ago | Apache-2.0 | A | 89 | Claude Code |