Borrowing it
Nothing to install: this file belongs to cesarnml/son-of-anton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cesarnml/son-of-anton/main/.agents/skills/son-of-anton-ethos/SKILL.mdgit clone --depth 1 https://github.com/cesarnml/son-of-antonWrote 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/cesarnml/son-of-anton/son-of-anton-ethos)<a href="https://agentmods.dev/skills/cesarnml/son-of-anton/son-of-anton-ethos"><img src="https://agentmods.dev/badge/skills/cesarnml/son-of-anton/son-of-anton-ethos/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/cesarnml/son-of-anton/son-of-anton-ethos"><img src="https://agentmods.dev/badge/skills/cesarnml/son-of-anton/son-of-anton-ethos.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 | $0.00089 | $0.03926 |
| Opus 5.5 | $0.00036 | $0.01570 |
| Sonnet 5.5 | $0.00018 | $0.00785 |
| Haiku 4.5 | $0.00009 | $0.00393 |
Grade A, and why
soa-son-of-anton-ethos 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Son Of Anton Ethos
Before executing a single command: Read docs/template/delivery/delivery-orchestrator.md in full. Every orchestrator action — for both ticket stacks (start, post-verify, write-subagent-adversarial-review, subagent-review, open-pr, poll-review, record-review, advance, triage-ticket) and standalone PRs (triage-standalone) — is defined there with exact sequencing and policy. That document is the authoritative command surface. Your own reasoning about what the flow "probably" is does not override it.
Son of Anton drives approved work to completion. How ticket boundaries are handled is governed by ticketBoundaryMode in orchestrator.config.json. The orchestrator does not seek repeated permission between tickets — but it honors the boundary contract precisely as configured.
Standalone PRs
- Entrypoint. Use
bun run deliver. - When to use. Smaller bounded changes ship as standalone PRs without a new phase/epic. Use
bun run deliver triage-standalone [--pr <number>]— not the ticketed stacked flow (--plan …,poll-review,advance, etc.). - Review discipline. Complete implement → fast verification (
bun run verify:quiet+ scoped tests as needed) → final publication gate (bun run ci:quietfor non-doc code changes) → named self-audit (re-read diff, second-pass risky areas). Standalone PRs do not use the ticket-onlypost-verifyorsubagent-reviewrecorders because the flow is stateless, so these remain expected preflight behaviors rather than orchestrator-enforced gates.- Self-audit is required for every standalone PR.
- For non-trivial code changes, invoke a review subagent via the Agent tool before
triage-standalone. Fill indocs/template/delivery/adversarial-review-template.mdfrom the diff and use it as the prompt — do not substitute a vague "find holes" directive. Doc-only or genuinely trivial changes may skip this step. - Standalone
triage-standaloneis the only orchestrator-visible review gate on this path. - If the change needs recorded self-audit / Codex gates to feel safe, it likely should not stay a standalone PR unless the repo first adds lightweight standalone review state.
- Running
triage-standalone. Uses real wall-clock polling. Surface that before starting; do not hide the time cost. - Commits. Follow AGENTS Pre-Commit (Prettier for touched files; spellcheck when docs or user-facing copy changed).
- Product-scope gates apply to new phase/epic work — not to standalone PRs already allowed outside a new phase.
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 · 184 lines · 89 tokens per session scan A c2a92c68efd7
soa-son-of-anton-ethos is a skill published in the GitHub repository cesarnml/son-of-anton (2 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 3,926 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…