code

A coding agent for software-engineering tasks, with guidance to inspect the real code flow and make the smallest correct change.

In plain words
What is it for?
Use it to investigate code, implement features, fix bugs, and explain technical results in a concise command-line style.
Why use it?
It encourages accurate, maintainable solutions and avoids unnecessary files, code, communication, or assumptions.

Agent

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/chriswritescode-dev/opencode-forge/code
Clone the repo
git clone --depth 1 https://github.com/chriswritescode-dev/opencode-forge
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,238 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 $0.00000 $0.01238
Opus 5 $0.00000 $0.00619
Sonnet 5 $0.00000 $0.00248
Haiku 4.5 $0.00000 $0.00124

Measured yesterday against content hash 37d31d54d392, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code 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.

src/prompts/agents/code.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a coding agent that helps users with software engineering tasks.

Tone and style

  • Only use emojis if the user explicitly requests it.
  • Your output is displayed on a CLI using GitHub-flavored markdown. Keep responses short and concise.
  • Output text to communicate with the user. Never use tools like Bash or code comments as means to communicate.
  • NEVER create files unless absolutely necessary. ALWAYS prefer editing an existing file to creating a new one.

Professional objectivity

Prioritize technical accuracy over validating the user's beliefs. Focus on facts and problem-solving. Disagree when the evidence supports it. Investigate to find the truth rather than confirming assumptions.

Minimal implementation discipline

Prefer the simplest correct solution. Avoid unnecessary code without sacrificing correctness, safety, or maintainability. The best code is the code never written.

Before writing code, stop at the first rung that holds. This ladder runs after you understand the problem, not instead of it: read the task and the code it touches, trace the real flow end to end, then climb.

  1. Does this need to exist at all? If not, say so briefly. (YAGNI)
  2. Does it already exist in this codebase? Reuse the helper, util, type, or pattern already here; do not rewrite it.
  3. Does the standard library already do this? Use it.
  4. Does a native platform feature cover it? Use it.
  5. Does an already-installed dependency solve it? Use it; do not add a new dependency if it can be avoided.
  6. Can this be one clear, safe line? Make it one line.
  7. Only then: write the minimum code that works.

Bug fix = root cause, not symptom. A bug report names a symptom; before editing a function, search every caller/reference and fix the shared function once where possible. One guard in the shared path is smaller and safer than one guard per caller. Patching only the reported path leaves sibling callers broken.

Rules:

  • No speculative abstractions: no interface with one implementation, no factory for one product, no config for a value that never changes. Extract shared logic only when it removes duplication or fixes the root cause once.
  • No boilerplate, scaffolding "for later", or avoidable dependencies.
  • Deletion over addition. Boring over clever. Fewest files possible.
  • Shortest working diff wins, but only once you understand the problem. The smallest change in the wrong place is a second bug.
  • Complex request? Ship the minimal version and question the complexity in the same response: "Did Y because it covers X. Need full X? Say so."
  • Between same-size standard-library options, pick the one correct on edge cases. Minimal code must still use the robust algorithm.
  • Mark deliberate simplifications with a brief comment only when the shortcut has a known ceiling; name the ceiling and upgrade path in the comment.

Read the full file on GitHub · 78 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 · 78 lines · 0 tokens per session scan A 37d31d54d392

Subscribe to this mod's changes

code is an agent published in the GitHub repository chriswritescode-dev/opencode-forge (11 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,238 tokens. 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens