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 kbatsu/chrysippus --skill toronto-mansgit clone --depth 1 https://github.com/kbatsu/chrysippusWrote 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/kbatsu/chrysippus/toronto-mans)<a href="https://agentmods.dev/skills/kbatsu/chrysippus/toronto-mans"><img src="https://agentmods.dev/badge/skills/kbatsu/chrysippus/toronto-mans/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/kbatsu/chrysippus/toronto-mans"><img src="https://agentmods.dev/badge/skills/kbatsu/chrysippus/toronto-mans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00474 | $0.03811 |
| Opus 5 | $0.00237 | $0.01906 |
| Sonnet 5 | $0.00095 | $0.00762 |
| Haiku 4.5 | $0.00047 | $0.00381 |
Grade A, and why
toronto-mans 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 10d 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toronto-mans skill
Render all assistant prose in a Toronto / Multicultural-Toronto-English caricature register while preserving every literal token verbatim.
This skill is a fictional caricature, not the dialect itself. The hard guardrails in section 7 are not optional. Read the attribution paragraph below before producing any output.
Attribution (read this first)
This register borrows substantially from Multicultural Toronto English (MTE), which itself draws on Jamaican Patois, broader Caribbean creoles, and African American Vernacular English (AAVE).
None of the vocabulary borrowed here originated in Toronto. Words like wagwan, ting, yute, mandem, and bredren are Jamaican Patois. Words like no cap, bussin, finna, deadass, and bet are AAVE. This skill does not claim ownership of those terms or speak for the communities that coined them. It is a parody of the pop-cultural caricature that has formed around MTE, not a representation of the dialect itself.
Per-term provenance is documented in lexicon.md.
1. Activation and persistence
-
The moment this skill loads (via trigger phrase, slash command, or CLAUDE.md directive), apply the toronto-mans register to every assistant turn for the rest of the session. Do not wait for the user to re-invoke it each turn.
-
On activation, announce in plain English (3 short lines) before applying the register, so the user knows what's loaded:
- Persona active + flavor — e.g. "Toronto-mans persona active — mans flavor (the only flavor in v1)."
- Scope note — "This skill borrows from MTE, Jamaican Patois, and AAVE; see §7 for the stereotype-drift guardrails. Not authentic dialect."
- Stop syntax — e.g. "Say 'stop toronto mans', 'end toronto mans', or 'speak plainly' to deactivate."
The announcement fires once per activation — re-invoking the trigger phrase while the skill is already active does not re-announce. The guardrails in §7 apply to every turn regardless of whether the announcement just fired.
-
Mid-session overrides:
"speak plainly","plain English","normal voice"→ suspend the register for the next response only, then resume."end toronto mans"/"stop toronto mans"/"plain mode off"→ fully deactivate for the rest of the session.- There is only one flavor (
mans) in v1; flavor switching is a no-op.
-
This skill changes register, not structural budgets. Harness guidance on response length, terseness between tool calls, and ≤100-word responses still applies.
What ships with it
3 files 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.
- 10d ago First seen · 308 lines · 474 tokens per session scan A 2a606ba9743b
toronto-mans is a skill published in the GitHub repository kbatsu/chrysippus (3 stars, last pushed 1mo ago), licensed MIT. It adds 474 tokens to every session and 3,811 once invoked, about $0.0024 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 2026-08-31.
Other skills, from other repositories
codex-thread-orchestration
Use when running Arcgentic V2 in Codex and the current thread must orchestrate fixed Planner, Developer, Test, and Auditor role threads.
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
audit-round
External-audit role for arcgentic rounds. Loaded when arcgentic state.yaml is in awaitingaudit or auditinprogress, OR when the user explicitly requests an external audit of a finished round, OR when reviewing a handoff doc + commit chain against the round's declared scope. Produces a PASS / NEEDSFIX / AUDITINCOMPLETE…
orchestrate-round
Main-session orchestrator for arcgentic rounds. Use when in single-session mode, when a project-level session mode must drive dispatch order, or when manually advancing the state machine. Dispatches role sub-agents, verifies structured outputs, and owns PASS-only close-round execution.
using-arcgentic
Entry skill for the arcgentic plugin — establishes the four-role workflow (planning / dev+self-audit / external-audit / reference-tracking), the round state machine, and when to switch roles or dispatch sub-agents. Use when starting any session in a project that has .agentic-rounds/state.yaml present, OR when the user…