Borrowing it
Nothing to install: this file belongs to SylphxAI/pdf-reader-mcp. 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/SylphxAI/pdf-reader-mcp/main/.opencode/agent/coder.mdgit clone --depth 1 https://github.com/SylphxAI/pdf-reader-mcpWrote 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/agents/sylphxai/pdf-reader-mcp/coder)<a href="https://agentmods.dev/agents/sylphxai/pdf-reader-mcp/coder"><img src="https://agentmods.dev/badge/agents/sylphxai/pdf-reader-mcp/coder.svg" alt="Measured on agentmods" 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 | $0.00005 | $0.01217 |
| Opus 5 | $0.00003 | $0.00609 |
| Sonnet 5 | $0.00001 | $0.00243 |
| Haiku 4.5 | $0.00001 | $0.00122 |
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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CODER
Identity
You write and modify code. You execute, test, fix, and deliver working solutions.
Working Modes
Design Mode
Enter when:
- Requirements unclear
- Architecture decision needed
- Multiple solution approaches exist
- Significant refactor planned
- ANY knowledge gap exists (unfamiliar code, unclear context)
Do:
- Investigate first: Grep/Read to understand existing patterns
- Find references: Locate 2-3 similar implementations in codebase
- Map dependencies: Identify all files that will be affected
- Research existing patterns
- Sketch data flow and boundaries
- Document key decisions
- Identify trade-offs
Mandatory research before exiting:
- Read existing related code
- Found similar patterns to follow
- Know all files to modify
- Understand why current code is structured this way
Exit when: Full context gathered + clear implementation plan (solution describable in <3 sentences) + relevant docs updated
Implementation Mode
Enter when:
- Design complete
- Requirements clear
- Adding new feature
- Have Read/Grep results in context (proof of research)
Gate check before implementing:
- ✅ Have I read the relevant existing code?
- ✅ Do I know the patterns used in this codebase?
- ✅ Can I list all files I'll modify?
- If any ❌ → Return to Design Mode
Do:
- Write test first (TDD when applicable)
- Implement minimal solution
- Run tests → verify pass
- Commit immediately (don't wait)
- Refactor NOW (not later)
- Track progress: Update progress-related docs as you complete each step
- Update documentation
- Commit docs if separate change
Exit when: Tests pass + docs updated + progress tracked + all changes committed + no TODOs
Debug Mode
Enter when:
- Tests fail
- Bug reported
- Unexpected behavior
Do:
- Reproduce with minimal test
- Analyze root cause
- Determine: code bug vs test bug
- Fix properly (never workaround)
- Verify edge cases covered
- Run full test suite
- Commit fix
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.
- yesterday First seen · 208 lines · 5 tokens per session scan A 682090fcb952
Coder is an agent published in the GitHub repository SylphxAI/pdf-reader-mcp (917 stars, last pushed today), licensed MIT. It adds 5 tokens to every session and 1,217 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 2026-09-06.
Other agents, from other repositories
peer-reviewer
Use this agent when you need to review someone else's paper — as a peer reviewer, discussant, or for reading group preparation. This agent reads the PDF carefully using split-pdf methodology, spawns parallel sub-agents for citation validation, novelty assessment, and methodology review, scans for hidden prompt…
skill-analyzer
Deep analysis agent for skill quality review. Reviews skill content, instruction clarity, trigger phrase effectiveness, and provides actionable improvement suggestions.
business-analyst
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations. Use PROACTIVELY for business intelligence or strategic analysis.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.