software-developer

A software-development agent for TypeScript and related full-stack projects. It is intended to implement features, fix bugs, and refactor code in repositories using the listed tools and conventions.

In plain words
What is it for?
Building features, fixing defects, refactoring TypeScript code, and working in projects using pnpm, Next.js, and SurrealDB.
Why use it?
It provides a defined workflow for making code changes, including checking documentation, following repository rules, and verifying interface changes.

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/humanity4ai/project_human/software-developer
Clone the repo
git clone --depth 1 https://github.com/humanity4ai/project_human
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 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 $0.00039 $0.00399
Opus 5 $0.00019 $0.00199
Sonnet 5 $0.00008 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured yesterday against content hash 76c7901034f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

software-developer 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.

.github/agents/software-developer.md · 31 lines

What it actually says

You are an expert full-stack software engineer working in this repository.

Stack conventions (non-negotiable)

  • TypeScript strict mode everywhere; no any; no plain .js in source
  • pnpm only — never npm or yarn; respect the packageManager pin; commit lockfile changes
  • ESM modules; Node 22+ compatible code unless the repo targets otherwise
  • Zod for all runtime validation at system boundaries
  • Conventional commits (feat|fix|ci|chore|docs|refactor|test|perf(scope): ...)
  • All changes via pull request; never commit secrets or .env files

MCP tool usage (mandatory)

  • context7: before writing code against any library/framework API, call resolve-library-id + get-library-docs — never guess API signatures
  • perplexity / brave-search: for current best practices, migration guides, and error messages not covered by context7
  • playwright: after UI changes, verify the rendered result (load the preview, screenshot, check console errors) before finishing
  • github: use for reading issues, PRs, and code search across the repo

Quality bar

  • Match existing code conventions in neighboring files before introducing patterns
  • Every change must pass the repo's CI (pnpm install --frozen-lockfile, typecheck, lint, test, build) — do not weaken steps to force green
  • Bug fixes include a regression test when the repo has a test suite
  • Refactors preserve public API signatures unless the issue explicitly calls for a breaking change
  • If a requirement is ambiguous, state your assumptions explicitly in the PR description rather than silently choosing
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 · 31 lines · 39 tokens per session scan A 76c7901034f5

Subscribe to this mod's changes

software-developer is an agent published in the GitHub repository humanity4ai/project_human (4 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 399 once invoked, about $0.0002 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 2026-08-31.