agent-creator

A guide for creating a project-specific Pythinker subagent, such as a migration reviewer or API contract checker. It covers the agent's configuration, instructions, and structured results.

In plain words
What is it for?
Use it to scaffold or design custom agents, choose their tools, define when they should be used, and specify the format of their output.
Why use it?
It helps you define a specialist that Pythinker can discover and delegate work to without changing the runtime or writing a new loader.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/pymodel/pythinker-cli/agent-creator
Any agent
npx skills add PyModel/pythinker-cli --skill agent-creator
Clone the repo
git clone --depth 1 https://github.com/PyModel/pythinker-cli

Made for: Claude Code, Codex.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00091 $0.01599
Opus 5 $0.00046 $0.00800
Sonnet 5 $0.00018 $0.00320
Haiku 4.5 $0.00009 $0.00160

Measured yesterday against content hash e3f6af9f3011, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-creator 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 yesterday.

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.

src/pythinker_code/skills/agent-creator/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Creator

Guide the user to a correct, immediately-loadable Pythinker agent definition. The hard part is not the file format — it is a sharp when_to_use, a scoped tool set, a persona that earns its keep, and a structured output contract. The builtin agents under src/pythinker_code/agents/default/ (plan.yaml, explore.yaml) are the quality bar; match them.

Do NOT invent a new loader or code path. Two existing, additive mechanisms already load custom agents — pick the one that fits and write a file. No changes to agentspec.py, the CLI, or the runtime are needed.

Two ways to define an agent

A. Markdown agent file (quick, auto-discovered) — preferred default

A single <name>.md placed in a discovery directory is auto-discovered on the next launch. Frontmatter fields recognized by parse_markdown_agent:

  • name — the agent name (falls back to the filename stem).
  • description — what it is (falls back to the first body line).
  • when_to_use — when the orchestrator should delegate to it (falls back to description).
  • tools — a YAML list of friendly tool names, mapped to import paths automatically — do NOT use the module:ClassName form here. The supported names are: Agent, Bash, Edit, Fetch, Glob, Grep, Read, TodoWrite, WebFetch, WebSearch, Write.
  • model — optional model alias.

The markdown body is the agent's system prompt (its persona + rules + output contract).

---
name: migration-reviewer
description: Reviews database/schema migrations for safety and reversibility.
when_to_use: Use when a change touches migration files, schema DDL, or data backfills.
tools: [Read, Grep, Glob, Bash]
---

You are a database-migration safety reviewer. You do NOT edit files.
... persona, rules, and a structured output contract ...

B. YAML agent spec (richer: inheritance, subagents, separate prompt file)

A agent.yaml + a separate system.md, loaded via --agent-file path/to/agent.yaml (or referenced as a subagent). Use this when you need extend inheritance, a subagents: block, or fine-grained allowed_tools / exclude_tools. Full AgentSpec fields (see agentspec.py):

Read the full file on GitHub · 123 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. yesterday First seen · 123 lines · 91 tokens per session scan A e3f6af9f3011

Subscribe to this mod's changes

agent-creator is a skill published in the GitHub repository PyModel/pythinker-cli (20 stars, last pushed 4d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,599 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

release-notes

Generate user-facing release notes for Intelligent Terminal. Use when asked to write release notes, changelog, what-is-new summary, or prepare a release. Compares git commits between releases, looks up PR-linked issues and community contributors, then outputs formatted notes with "Verbed + Impact + Scenario" style…

microsoft/intelligent-terminal · 73 tokens

peer-review

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…

xintaofei/codeg · 71 tokens

scientific-critical-thinking

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…

xintaofei/codeg · 63 tokens

statistical-analysis

Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…

xintaofei/codeg · 111 tokens

statistical-power

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…

xintaofei/codeg · 190 tokens

pr-integration-test

Design, implement, and validate Intelligent Terminal integration tests for a target pull request or regression. Use when asked to add PR integration tests, convert a bug fix into E2E coverage, prove existing behavior still works, map tests to the release checklist, or verify E2E reports mark checklist cases complete.

microsoft/intelligent-terminal · 66 tokens