agentmods.dev

create-new-agent

create-new-agent is a skill for Claude Code, Codex from XAIHT/Tlamatini. It costs 164 tokens per session (3,020 once invoked), scanned A, original, MIT.

A step-by-step guide for adding a new workflow agent to the Tlamatini application, including its backend, web interface, configuration, database entry, styling, and documentation.

In plain words
What is it for?
Use it when creating or renaming a Tlamatini workflow agent and checking that the implementation follows the project's required structure.
Why use it?
It provides one agreed checklist for the many files and registration points needed to add an agent correctly.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Current release: **[v1.90.0](../../../../docs/changes/2026-10-22-v1.90.0.md)**. Dated records below retain their original evidence dates..

not rated 15repo changed today A scan SkillSpector: pass 164 tokens original MIT

Good fit Use it when creating or renaming a Tlamatini workflow agent and checking that the implementation follows the project's required structure.

Compare 6 skills from other repositories ↓
View source ↗ XAIHT/Tlamatini xaiht.org
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/XAIHT/Tlamatini
agentmods
npx agentmods add skills/xaiht/tlamatini/create_new_agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for create-new-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/xaiht/tlamatini/create_new_agent/github.svg)](https://agentmods.dev/skills/xaiht/tlamatini/create_new_agent)
Your own site
<a href="https://agentmods.dev/skills/xaiht/tlamatini/create_new_agent"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/create_new_agent/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.

agentmods 80×15 button for create-new-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/xaiht/tlamatini/create_new_agent"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/create_new_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,020 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00164 $0.03020
Opus 5.5 $0.00066 $0.01208
Sonnet 5.5 $0.00033 $0.00604
Haiku 4.5 $0.00016 $0.00302

Measured today against content hash e4fbf5372693, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-new-agent 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 today.

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.

Tlamatini/agent/skills_pkg/create_new_agent/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create New Agent — canonical reference

Current release: v1.90.0. Dated records below retain their original evidence dates.

HEADLESS IS FORBIDDEN. VISIBLE FOREGROUND EXECUTION ONLY. Every command, automated test, diagnostic, script, build, agent and browser must run in a visible foreground window on Angela's real desktop. Use forked CMD/PowerShell windows, execute_forked_window: true, and headless: false. Monitor live; if visibility cannot be confirmed, do not run. Read the mandatory execution policy.

The full, ground-truth procedure for adding or renaming a Tlamatini workflow agent lives in a single file at the repo root:

Tlamatini/.agents/workflows/create_new_agent.md

That document is the single source of truth for the 8-step agent contract:

  1. Backend agent script — agent/agents/<name>/<name>.py + config.yaml (copy shoter.py boilerplate; FOR_DISABLE_CONSOLE_CTRL_HANDLER=1 must be the first line; implement _IS_REANIMATED; if the agent feeds Parametrizer, emit INI_SECTION_<TYPE><<< blocks).
  2. Django view + URL — update_<name>_connection_view in agent/views.py and the matching agent/urls.py route.
  3. Migration — agent/migrations/00NN_add_<name>.py seeds the Agent row whose agentDescription is the display name (the canvas renders it verbatim).
  4. CSS gradient — a 4-color .canvas-item.<css-class>-agent block in agentic_control_panel.css plus the hover variant. Sidebar styling inherits via applyAgentToolIconStyle().
  5. JavaScript — four files: acp-agent-connectors.js, acp-canvas-core.js (6 locations: classMap, AGENTS_NEVER_START_OTHERS, removeConnection, removeConnectionsFor, mouseup handler), acp-canvas-undo.js, acp-file-io.js.
  6. agentic_skill.md — append an entry so FlowCreator's AI flow-designer knows the new agent exists.
  7. README.md — agent count, structure listing, classification, workflow table, glossary, changelog, API table. Also update agents_descriptions.md (the page's agent_purpose_map source).
  8. Lint — python -m ruff check (zero errors) and npm run lint (fix errors only).

Read the full file on GitHub · 157 lines

Changes

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.

  1. today Changed e4fbf5372693
  2. 2d ago Changed · +14 lines 58659ffe2243
  3. 3d ago Changed e87864e0f104
  4. 4d ago Changed c7f90d77e0e0
  5. 5d ago Changed · +3 lines 80f42c1cceec
  6. 26d ago Changed 67ac9ff315d6
  7. 29d ago Changed · +2 lines 94f9bf46eadd
  8. 1mo ago Changed · +28 lines 4e73f7b795bc
  9. 1mo ago Changed · +8 lines a4b89e0221bf
  10. 1mo ago First seen · 102 lines · 164 tokens per session scan A a74334499133

Subscribe to this mod's changes

create-new-agent is a skill published in the GitHub repository XAIHT/Tlamatini (15 stars, last pushed yesterday), licensed MIT. It adds 164 tokens to every session and 3,020 once invoked, about $0.0007 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.

Building agentsagentagentic-aiai-assistantcoding-assistantdeveloper-toolsdjango
Related

Other skills, from other repositories

commit

Inspect git status, draft a commit message that matches the repo's style, and commit staged changes.

mochow13/keen-code · 22 tokens

review

Review current code changes for bugs, regressions, test gaps, and project-guideline violations.

mochow13/keen-code · 21 tokens

artifact-deploy

One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".

kirodotdev/KiroCrew · 74 tokens

explain-for

Explain a topic, code, error or design decision for one named audience (a 5-year-old, a manager, a designer, a grad student, a parent). Resolves who it is for, pins the ground truth first, then tunes vocabulary, analogy, tone and depth to that audience. Use when an audience is named.

kirodotdev/KiroCrew · 71 tokens

papyrus-latex-suggestions

Propose inline replacement text (old -> new) as accept/reject suggestions, LaTeX 'suggesting mode' / track changes, rendered in the PDF. Use when the author wants concrete edit proposals to accept or reject. For remarks ABOUT the text rather than replacements, use papyrus-latex-comments.

kirodotdev/KiroCrew · 69 tokens

pptagent

Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.

icip-cas/PPTAgent · 52 tokens