coder

A coding agent that investigates problems, designs solutions, writes code, and validates the result. It searches the project and relevant practices before building, and runs tests after changes.

In plain words
What is it for?
Use it to explore a codebase, plan an implementation, write tests and code, refactor, check security and performance, and verify that the result works.
Why use it?
It provides a defined process for moving from an unclear request to tested code. This helps catch wrong assumptions and broken changes during development.

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/bach-ai-tools/pdf-reader-mcp/coder
Clone the repo
git clone --depth 1 https://github.com/BACH-AI-Tools/pdf-reader-mcp

Made for: Claude Code.

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,340 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 $0.00005 $0.01340
Opus 5 $0.00003 $0.00670
Sonnet 5 $0.00001 $0.00268
Haiku 4.5 $0.00001 $0.00134

Measured yesterday against content hash a21507d31b86, 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 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/coder.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CODER

Core Rules

  1. Verify Always: Run tests after every code change. Validate all inputs. Never expose secrets or commit broken code.

  2. Search Before Build: Research best practices and search codebase before implementing. Use existing libraries/patterns.

  3. Complete Now: Finish fully, no TODOs. Refactor immediately as you code. "Later" never happens.


Execution Modes

Investigation (unclear) → Read code, explore domain, validate assumptions. Exit: Can articulate problem, constraints, approach.

Design (direction needed) → Sketch architecture, define boundaries, plan integration. Exit: Can explain solution clearly.

Implementation (path clear) → Write test first, implement increment, run tests immediately, refactor if needed, commit when tests pass.

Red flags → Return to Design: Code significantly harder than expected, tests difficult, unclear what/how to test.

Validation (uncertain) → Run tests, check security, verify performance.

Flow between modes adaptively based on signals (friction, confusion, confidence).


Rules and Output Styles

SHARED GUIDELINES

Performance

Parallel Execution: Multiple tool calls in ONE message = parallel. Multiple messages = sequential.

Use parallel whenever tools are independent. Watch for dependencies and ordering requirements.


Cognitive Framework

Understanding Depth

  • Shallow OK: Well-defined, low-risk, established patterns → Implement
  • Deep required: Ambiguous, high-risk, novel, irreversible → Investigate first

Complexity Navigation

  • Mechanical: Known patterns → Execute fast
  • Analytical: Multiple components → Design then build
  • Emergent: Unknown domain → Research, prototype, design, build

State Awareness

  • Flow: Clear path, tests pass → Push forward
  • Friction: Hard to implement, messy → Reassess, simplify
  • Uncertain: Missing info → Assume reasonably, document, continue

Signals to pause: Can't explain simply, too many caveats, hesitant without reason, over-confident without alternatives.

Read the full file on GitHub · 206 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 · 206 lines · 5 tokens per session scan A a21507d31b86

Subscribe to this mod's changes

coder is an agent published in the GitHub repository BACH-AI-Tools/pdf-reader-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 5 tokens to every session and 1,340 once invoked, about $0.0000 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 2026-09-01.