developer

A set of development rules for GitHub Agentic Workflows, covering file organization, engine separation, tests, and when to split files.

In plain words
What is it for?
It helps organize Go files, separate AI engines, place tests beside implementation, and choose whether new functionality belongs in an existing or new file.
Why use it?
It gives contributors consistent decisions about where code and tests belong as the project grows.

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/github/gh-aw/developer
Clone the repo
git clone --depth 1 https://github.com/github/gh-aw
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,704 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 $0.00009 $0.03704
Opus 5 $0.00005 $0.01852
Sonnet 5 $0.00002 $0.00741
Haiku 4.5 $0.00001 $0.00370

Measured yesterday against content hash 7bbe4de59f0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/developer.instructions.md · 512 lines

How it starts

The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Instructions

Guidelines, patterns, and standards for GitHub Agentic Workflows.


Code Organization Patterns

1. Create Functions Pattern (create_*.go)

One file per GitHub entity. Examples: create_issue.go, create_pull_request.go, create_discussion.go, create_code_scanning_alert.go, create_agent_task.go.

2. Engine Separation Pattern

Each AI engine in its own file; shared helpers in engine_helpers.go. Examples: copilot_engine.go, claude_engine.go, codex_engine.go, custom_engine.go.

3. Test Organization Pattern

Tests alongside implementation:

  • Feature: feature.go + feature_test.go
  • Integration: feature_integration_test.go
  • Scenario: feature_scenario_test.go

File Creation Decision Tree

graph TD
    A[Need New Functionality?] --> B{Size > 200 lines?}
    B -->|Yes| C[Create New File]
    B -->|No| D{Related to Existing File?}
    D -->|Yes| E[Add to Existing File]
    D -->|No| C
    C --> F{Multiple Related Operations?}
    F -->|Yes| G[Use Create Pattern: create_*.go]
    F -->|No| H[Use Domain Pattern]
    E --> I{File > 1000 lines?}
    I -->|Yes| J[Consider Splitting]
    I -->|No| K[Keep in Same File]

File Size Guidelines

  • Small (50-200 lines): Utilities, helpers, simple features
  • Medium (200-500 lines): Domain-specific logic, focused features
  • Large (500-1000 lines): Complex features, comprehensive implementations
  • Very Large (1000+ lines): Consider splitting if not cohesive

Validation Architecture

Validates workflow configs before compilation. Centralized in validation.go, or domain-specific in dedicated files.

Workflow YAML → parser → validation (centralized + domain-specific) → compiler on pass, error report on fail.

Centralized Validation: pkg/workflow/validation.go

  • validateExpressionSizes() — GitHub Actions expression size limits
  • validateContainerImages() — Docker images accessible
  • validateRuntimePackages() — runtime package deps
  • validateGitHubActionsSchema() — GitHub Actions YAML schema
  • validateNoDuplicateCacheIDs() — unique cache IDs
  • validateSecretReferences() — secret reference syntax
  • validateRepositoryFeatures() — repo capabilities (issues, discussions)

Read the full file on GitHub · 512 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 · 512 lines · 9 tokens per session scan A 7bbe4de59f0e

Subscribe to this mod's changes

developer is an agent published in the GitHub repository github/gh-aw (5,050 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 3,704 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 2026-08-30.

Related

Other agents, from other repositories

devops-engineer

CI/CD, deployment, and infrastructure automation specialist.

ChanningLua/prax-agent · 14 tokens

checker-engineer

Use when a diff, planned change, or OpenSpec proposal touches the checker kernel — packages/claims/src/checkClaims.ts, witness.ts, wiring.ts, rules.ts, or config.ts — and you need a review of whether the change respects the kernel's own semantics: which verdict union a new verdict belongs to, whether its pass/fail…

armanfatemi/nullius · 275 tokens

retro-writer

Use as the FINAL stage of a proposal-to-pr run to record what happened, as one retrospective file under .claude/retrospectives/. Dispatched fresh, having NOT done the work, so it reads artefacts — the pipeline state file, review-evidence.md and its ## Probe — stage 2 score, progress.md, git history — rather than the…

armanfatemi/nullius · 252 tokens

github-actions-expert

Designs reliable GitHub Actions workflows with matrix builds, caching strategies, and secure deployment pipelines.

NickCrew/Claude-Cortex · 24 tokens

present-agent

An agent that exists, so the skill dispatching to it resolves.

armanfatemi/nullius · 2 tokens

bolt

Learning: Checking a file path against multiple GlobSets sequentially is less efficient than combining them into a single GlobSet and checking match indices. A single automaton pass (Aho-Corasick) is faster than multiple passes, even if the total number of patterns is the same. Action: When classifying strings against…

EffortlessMetrics/xchecker · 0 tokens