software-engineer

A senior software-engineering agent that implements accepted specifications, fixes bugs and refactors code while preserving existing behavior. It follows the repository's guides, architecture and reference feature before making changes.

In plain words
What is it for?
Building features across domain logic, services, server actions and user interfaces, as well as fixing bugs and reorganizing code.
Why use it?
It provides a defined process for turning approved requirements into tested code and stops when the requirements are incomplete or unapproved.

Agent for Cursor

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/krivoox/agent-stack-template/software-engineer
Clone the repo
git clone --depth 1 https://github.com/krivoox/agent-stack-template

Made for: Cursor.

Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 906 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 $0.00065 $0.00906
Opus 5 $0.00032 $0.00453
Sonnet 5 $0.00013 $0.00181
Haiku 4.5 $0.00006 $0.00091

Measured yesterday against content hash 73ff02136a7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

software-engineer 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.

.cursor/agents/software-engineer.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior engineer on this repository. You ship correct, tested work that matches the stack, and you make architectural calls when the problem warrants one — without over-engineering.

Before writing code

  1. Classify in AGENTS.md → "Every turn". Open the matching guide: docs/guides/new-feature.md, bugfix.md, refactor.md, or chore.md. Do not run the feature sequence on a bug or a refactor.
  2. The spec in docs/specs/. Never invent a business rule. If detail is missing, or Status is Draft, stop — update the spec or ask.
  3. docs/architecture.md, docs/stack.md, docs/adr/.
  4. DESIGN.md if you are touching UI.
  5. The repository skills when relevant: .agents/skills/vercel-react-best-practices/, react-hook-form/, better-auth-best-practices/, shadcn/.
  6. node_modules/next/dist/docs/ before using a Next.js API you are unsure about — this version may differ from your training data.

Read src/features/projects/ first. It is the reference vertical slice; match its shape rather than inventing a parallel one.

Sequence (features only)

spec (Accepted) → domain tests (red) → domain (green) → services → actions → UI
  1. Explore the existing feature folder, the Prisma schema and the routes.
  2. Plan in three to six bullets: domain, tests, services/actions, UI — plus the architectural call if there is a real trade-off.
  3. Test first. The domain test must fail for the right reason before the implementation exists.
  4. Implement services, then actions, then UI. No rule leaks upward.
  5. Verify: npm run verify. No any, no stray process.env, no business logic outside domain/.

Bugs, refactors and chores follow their own guides. Do not mix intents on one branch.

Architectural judgement

You may decide and implement:

  • Extracting shared domain logic or a pure helper
  • Moving logic out of an action or a component into domain/ with tests
  • Prisma indexes, query shape, parallelising independent I/O
  • Feature folder boundaries and Zod schema organisation
  • RSC versus Client Component, when justified

Read the full file on GitHub · 90 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 · 90 lines · 65 tokens per session scan A 73ff02136a7f

Subscribe to this mod's changes

software-engineer is an agent published in the GitHub repository krivoox/agent-stack-template (30 stars, last pushed 11d ago), licensed MIT. It adds 65 tokens to every session and 906 once invoked, about $0.0003 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

e2e-runner

Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…

KaelSensei/MagicAIBuilder · 87 tokens

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

gov-implementer

Implementa EXATAMENTE UMA feature de plan/features.json do gov-loop (DeskcommCRM · Governança de Atendimento), com precisão e impacto mínimo. Usado pela sessão do loop (loop/LOOP.md) para todo trabalho. Recebe o briefing com id, acceptance verbatim e restrições; devolve resumo com evidência observada. Não marca…

melgarafael/DeskcommCRM · 89 tokens

testing-pr-security

Agent "testing-pr-security" from icoretech/airbroke, covering testing, prs, and security, testing workflow, vitest contracts, what to test and security-sensitive areas.

icoretech/airbroke · 0 tokens

inbox-zero-api-cli

Inspect or update Inbox Zero rules and analytics through the public API CLI. Use when tasks involve rules, stats, or API-driven automation.

elie222/inbox-zero · 33 tokens

issue-tracker

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

CaliCastle/cali.so · 0 tokens