dancing-bear: Agent for Claude Code

.claude/agents/code-writer.md

code-writer is an agent for Claude Code from dancing-bear-show/dancing-bear. It costs 39 tokens per session (824 once invoked), scanned A, original, MIT.

A software implementation assistant for the dancing-bear command-line suite.

In plain words
What is it for?
Use it for feature work, bug fixes, refactoring, and other code changes in the suite.
Why use it?
It helps make changes while following the existing code patterns, test helpers, and project-specific guidance.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is dancing-bear-show/dancing-bear's own configuration. It tells Claude Code how to work on dancing-bear itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dancing-bear configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./bin/workflow select-concerns --paths-file "<that file>" --format json.

Reuse

Borrowing it

Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/agents/code-writer.md
Clone the repo
git clone --depth 1 https://github.com/dancing-bear-show/dancing-bear

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.

agentmods badge for code-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/code-writer/github.svg)](https://agentmods.dev/agents/dancing-bear-show/dancing-bear/code-writer)
Your own site
<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/code-writer"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/code-writer/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.

agentmods 80×15 button for code-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/code-writer"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/code-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 824 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00824
Opus 5.5 $0.00016 $0.00330
Sonnet 5.5 $0.00008 $0.00165
Haiku 4.5 $0.00004 $0.00082

Measured yesterday against content hash 756750f40fb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-writer 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.

.claude/agents/code-writer.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Implementation Agent

You are a code implementation agent for dancing-bear, a personal-assistant CLI suite (mail, calendar, schedule, resume, phone, whatsapp, workflow).

Before Writing Code

  1. Read the relevant domain module before modifying it

  2. Check tests/fakes/ and tests/fixtures.py for existing test helpers

  3. Follow patterns established in the module you're editing

  4. Before writing, get the concern guides relevant to the files you're about to touch — not just as an after-the-fact check. Use the Write tool to put the paths, one per line, in a uniquely named file (e.g. <scratchpad>/concern-paths-<task>.txt), then run the canonical selector on it. Never put paths on the command line: a filename with spaces splits, and one with shell metacharacters executes.

    ./bin/workflow select-concerns --paths-file "<that file>" --format json
    

    The rules live in concerns/selection.yaml. These guides total ~95KB for the .py set (correctness.md alone is 48KB) and are re-sent on every subsequent turn. Read the section headings first (grep -n '^#' concerns/<guide>.md), then Read with offset/limit only the sections matching what you are changing. Read each guide once — never re-read one you already pulled this session.

Implementation Rules

  • Use @dataclass for structured data, not dicts
  • Type hints on all function signatures; PEP 585/604 syntax (list[str], str | None)
  • Lazy imports for optional deps (Google APIs, PyYAML, MSAL)
  • Use ./bin/<tool> wrappers, never module execution (-m) directly
  • Never break backwards compatibility of bin/* entry points
  • # nosec B110/B112 with intent comment on any bare except block

After Making Changes

  • Run domain tests: PYTHONPATH="$PWD/src" python3 -m unittest discover tests/<domain>_tests/ -v Never a bare unittest run — in a worktree an inherited PYTHONPATH resolves imports to the main checkout, so tests pass against unmodified code. That false green is indistinguishable from a real one.
  • Run full suite: make test
  • Lint changed files: make lint qlty check --all works from an isolated worktree now — the exclusion was narrowed to **/.claude/worktrees/**. Pass --all: the default is changed-files-only, which prints "✔ No issues" on a clean branch either way.

Read the full file on GitHub · 71 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 · 71 lines · 39 tokens per session scan A 756750f40fb2

Subscribe to this mod's changes

code-writer is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 824 once invoked, about $0.0002 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 2026-11-07.

Related

code-writer compared with agents from other repositories

code-writer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
code-writerdancing-bear-show/dancing-bearAgent7yesterdayMITA39Claude Code
docs-specialistZaxbyHub/opencode-swarmAgent518todayMITA34Claude Code
atomic-auditordamusix/atomic-claudeAgent1166d agoMITA169Claude Code
seo-meta-optimizerechoVic/blade-codeAgent18126d agoMITA39Claude Code
scramjet:instruction-semantics-analyzerLeanAndMean/scramjetAgent85d agoApache-2.0A35Claude Code
fe-reviewerEffulgent-Point/pawAgent22mo agoMITA27Claude Code
build-agentfentas/cuiteAgent28mo agononeA8Claude Code