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 agentmods add skills/pymodel/pythinker-cli/customize-pythinkernpx skills add PyModel/pythinker-cli --skill customize-pythinkergit clone --depth 1 https://github.com/PyModel/pythinker-cliWhat 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 | $0.00098 | $0.01401 |
| Opus 5 | $0.00049 | $0.00700 |
| Sonnet 5 | $0.00020 | $0.00280 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
customize-pythinker 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customize Pythinker
Authoritative, offline schema for editing Pythinker's own configuration surface. Pythinker
hard-fails on a malformed config, so get the schema right the first time. This skill covers the
config surfaces no other builtin skill owns. Out of scope: authoring agents (use agent-creator),
authoring skills (use skill-creator).
Always verify a value against the real schema before writing it. After any edit, confirm Pythinker still starts (a malformed file aborts startup).
Agent YAML (agentspec.py)
An agent spec is a YAML file with a separate system-prompt markdown file. Inheritance lets a project agent extend the builtin one.
| Field | Type | Notes |
|---|---|---|
extend |
str | Agent file to inherit from. "default" inherits the builtin agent. Child fields override parent; system_prompt_args merge by key; subagents merge with child entries winning. |
name |
str | Required (or inherited via extend). |
system_prompt_path |
path | Required; resolved relative to the YAML file. |
system_prompt_args |
dict[str,str] | Conventionally carries ROLE_ADDITIONAL (persona text). Merged when extending. |
tools |
list[str] | module:ClassName form, e.g. pythinker_code.tools.file:ReadFile. |
allowed_tools / exclude_tools |
list[str] | Narrow the inherited/declared tool set. |
model |
str | Optional model alias. |
mode |
primary | subagent | all | hidden |
Defaults to primary. |
hidden |
bool | Optional; hides the agent from default selection. Distinct from mode: hidden. |
steps |
int ≥ 1 | Max steps per turn. |
temperature |
float 0–2 | Optional. |
top_p |
float 0–1 | Optional. |
when_to_use |
str | Delegation guidance for the orchestrator. |
subagents |
dict[name → {path, description}] | Child subagent map. |
Project agents are auto-discovered as *.md files (Claude-style frontmatter) in, by precedence:
.pythinker/agents/ > .claude/agents/ > .agents/agents/ > .codex/agents/. A markdown agent
whose name matches a builtin subagent type is skipped (the builtin wins); use a distinct name.
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.
- yesterday First seen · 114 lines · 98 tokens per session scan A f623124e1350
customize-pythinker is a skill published in the GitHub repository PyModel/pythinker-cli (20 stars, last pushed 4d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,401 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.
Other skills, from other repositories
skill-creator
Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.
multi-cli-runtime
Internal helper contract for calling the multi-cli-companion runtime from any multi: subagent.
customize
Rewire which CLI handles which role in cc-multi-cli-plugin, OR diagnose/work around an upstream CLI quirk via env vars and config files. Use when the user asks to swap CLIs, change a subagent's target CLI, add or disable a subagent or command, restrict a CLI to read-only, hardcode a model, or change how a role frames…
subagent-manager
Use when the user mentions "subagent" commands, wants to coordinate worker agents, or asks to delegate tasks to a team of agents using subagent-cli. Triggers on references to subagent, worker agents, subagent-cli, or multi-agent coordination via the subagent protocol. Also use when the user says things like "チームで進めて"…
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…