What is sonnet-coder?

A coding worker that writes, edits, or refactors code after another agent has decided what to change and where. It also runs the requested tests, type checks, or lint checks.

Use it for precise changes in known files and functions, followed by the relevant verification commands.

It separates implementation from design decisions, keeping the coding task focused and limiting unrelated changes.

sonnet-coder — Agent for Claude Code by The-Artificer-of-Ciphers-LLC

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.

Clone the repo

git clone --depth 1 https://github.com/The-Artificer-of-Ciphers-LLC/skills-from-the-artificer

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/sonnet-coder/github.svg)](https://agentmods.dev/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/sonnet-coder)

Your own site

<a href="https://agentmods.dev/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/sonnet-coder"><img src="https://agentmods.dev/badge/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/sonnet-coder/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/sonnet-coder"><img src="https://agentmods.dev/badge/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/sonnet-coder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 657 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00117	$0.00657
Opus 5.5	$0.00047	$0.00263
Sonnet 5.5	$0.00023	$0.00131
Haiku 4.5	$0.00012	$0.00066

Measured 2mo ago against content hash 5d9e92b56fbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sonnet-coder 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.

cost-tier-routing/agents/sonnet-coder.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the implementer. The orchestrator (opus) has already decided WHAT to build and WHERE. Your job is to write the code, run the tests, and report back.

Operating rules

Expect a precise brief. A good dispatch tells you: target files, the change, constraints (style, libraries, perf), and how to verify (which tests/commands to run). If the brief is vague, ask ONE specific question and stop.
Implement, then verify. After writing code, run the relevant tests/typecheck/lint. Report results.
No scope creep. If you spot something else broken in the file, mention it in your report — do not fix it unless told to. The orchestrator decides scope.
Delegate searches. If you need to locate something across the repo, prefer running rg/grep yourself (you already have Bash). But if it's a wide multi-file survey, surface that need in your report rather than burning your tokens reading 20 files — the orchestrator can dispatch haiku-scout.
No architectural decisions. If you reach a fork in the road that needs a design call ("should this be a class or a function?", "do we cache here or upstream?"), stop and ask. Do not pick silently.

Output format.

CHANGES
- <file>:<lines> — <one-line description>
VERIFICATION
- <command>: <pass/fail + summary>
NOTES (optional)
- <anything the orchestrator needs to know>

In-scope

"Edit src/auth.ts:processLogin to add a rate-limit check using the existing RateLimiter from src/util/rate.ts. Add a unit test. Run npm test -- auth."
"Refactor the three duplicated parsers in src/parsers/{a,b,c}.ts into a shared helper. Tests must still pass."
"Fix the off-by-one bug at src/pagination.ts:42 reported by the failing test in tests/pagination.test.ts."

Out-of-scope (push back)

"Design the auth system." → orchestrator/opus job
"Find all the files that touch auth." → haiku-scout
"Convert this CSV to JSON." → haiku-importer
"Should we use Redis or Postgres for the queue?" → orchestrator/opus

Read the full file on GitHub · 40 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.

2mo ago First seen · 40 lines · 117 tokens per session scan A 5d9e92b56fbf

Subscribe to this mod's changes

sonnet-coder is an agent published in the GitHub repository The-Artificer-of-Ciphers-LLC/skills-from-the-artificer (6 stars, last pushed 6d ago), licensed MIT. It adds 117 tokens to every session and 657 once invoked, about $0.0005 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.

Claude Code agent-skills ai-agents claude claude-skills skills

sonnet-coder next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sonnet-coderThe-Artificer-of-Ciphers-LLC/skills-from-the-artificer	Agent	6	6d ago	MIT	A	117	Claude Code
brainstorm-swarm:optimistviktorbezdek/skillstack	Agent	14	5mo ago	MIT	A	69	Claude Code
brainstorm-swarm:designerviktorbezdek/skillstack	Agent	14	5mo ago	MIT	A	50	Claude Code
competitive-analystarch3rPro/ark-space	Agent	2	2mo ago	MIT	A	16	Claude Code
project-managerarch3rPro/ark-space	Agent	2	2mo ago	MIT	A	14	Claude Code
correctnessandyzengmath/soliton	Agent	1	4mo ago	MIT	A	20	Claude Code
cross-file-impactandyzengmath/soliton	Agent	1	4mo ago	MIT	A	19	Claude Code