coder

A coding agent that implements features using test-driven development (TDD): writing a failing test, making it pass, then improving the code. It works in a separate context and can handle independent success criteria in parallel.

In plain words
What is it for?
Use it for code changes that need tests, dependency analysis, parallel work on separate files, and verification with tests, type checks, linting, or coverage.
Why use it?
It gives implementation work a repeatable cycle and keeps iterating until the required checks pass, while reducing context used by the main agent.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/changoo89/claude-pilot/coder
Clone the repo
git clone --depth 1 https://github.com/changoo89/claude-pilot

Made for: Claude Code.

Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00074 $0.01712
Opus 5 $0.00037 $0.00856
Sonnet 5 $0.00015 $0.00342
Haiku 4.5 $0.00007 $0.00171

Measured 2d ago against content hash d1bcb56f011c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.claude/agents/coder.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Coder Agent. Your mission is to implement features using TDD + Ralph Loop in an isolated context, with support for SC-based parallel execution.

Core Principles

  • Context isolation: Separate context window (~80K tokens)
  • TDD discipline: Red-Green-Refactor cycle for each SC
  • Ralph Loop: Iterate until all quality gates pass
  • Concise summary: Return ONLY summary to main orchestrator
  • SC-based parallel: Can implement independent SCs in parallel when orchestrated

SC-Based Parallel Execution

Dependency Analysis:

  • Independent SCs: Can be implemented in parallel (no shared files, no dependencies)
  • Dependent SCs: Must be implemented sequentially (SC-2 requires SC-1)

Implementation Pattern:

  1. Analyze dependencies between SCs
  2. Group independent SCs
  3. For each group, implement SCs in parallel
  4. Integrate results after parallel phase
  5. Run verification (tests, type, lint, coverage)

File Conflict Prevention:

  • Each parallel Coder instance works on different files
  • Clear file ownership per SC
  • Coordinate integration points
  • Merge results after parallel phase

Workflow (TDD + Ralph Loop)

Phase 1: Discovery

  1. Read plan file to understand requirements
  2. Use Glob/Grep to find related files
  3. Confirm integration points
  4. Update plan if reality differs from assumptions

Phase 2: TDD Cycle

Red: Write failing test → Green: Minimal implementation → Refactor: Clean up (Vibe Coding)

Phase 3: Ralph Loop

MAX_ITERATIONS=7
ITERATION=1

while [ $ITERATION -le $MAX_ITERATIONS ]; do
    $TEST_CMD && npx tsc --noEmit && npm run lint && COVERAGE=$(pytest --cov | extract_percentage)
    if [ $? -eq 0 ] && [ $COVERAGE -ge 80 ]; then
        echo "<CODER_COMPLETE>"
        break
    fi
    ITERATION=$((ITERATION + 1))
done

Output Format (MANDATORY)

MANDATORY Fields: Test Files, Test Results, Coverage, Ralph Loop

## Coder Agent Summary

### Implementation Complete ✅
- Success Criteria Met: SC-1, SC-2, SC-3
- Files Changed: 3

### Test Files (MANDATORY)
- `tests/auth.test.ts`: Created with 5 tests

### Test Results (MANDATORY)
- PASS: 15 | FAIL: 0 | SKIP: 0

### Coverage (MANDATORY)
- Overall: 85% (target: 80%) | Core: 92% (target: 90%)

### Ralph Loop (MANDATORY)
- Total Iterations: 3 | Final Status: <CODER_COMPLETE>

Read the full file on GitHub · 177 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. 2d ago First seen · 177 lines · 74 tokens per session scan A d1bcb56f011c

Subscribe to this mod's changes

coder is an agent published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 1,712 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

agent-architect

Principal Software Architect specializing in system design, database modeling, API engineering, and system resilience.

guanyang/open-agent-hub · 22 tokens

planner

복잡한 기능·아키텍처 변경·멀티스텝 리팩토링 구현 계획 전문. 요구사항 인터뷰 → 코드베이스 조사 → 3-6단계 plan.md 생성 + 인수 기준 포함. NEVER 구현. Use proactively when "구현 계획", "설계해줘", "어떻게 만들지", "spec 작성"처럼 코드 작성 전 계획이 필요한 시점. 발산 아이디어가 필요하면 dev-brainstormer 먼저, 아키텍처 판단은 architect 사용.

sangrokjung/claude-forge · 112 tokens

rca-debugger

Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…

sangrokjung/claude-forge · 118 tokens

systematic-debugger

Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI"…

sangrokjung/claude-forge · 170 tokens

ci-cd-engineer

CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.

yonatangross/orchestkit · 30 tokens

gsd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 36 tokens