developer-guidelines

A set of rules for developers working on coding-agent tasks, emphasizing precise scope, documentation, security, and verification.

In plain words
What is it for?
Use it to guide implementation, testing, documentation, and handling of architectural or security-sensitive changes.
Why use it?
It helps prevent unrequested refactoring, speculative features, skipped tests, and changes that ignore project instructions.

Skill for Claude CodeCodex

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 skills/matrixfounder/agentic-development/developer-guidelines
Any agent
npx skills add MatrixFounder/Agentic-development --skill developer-guidelines
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,461 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 $0.00023 $0.03461
Opus 5 $0.00012 $0.01731
Sonnet 5 $0.00005 $0.00692
Haiku 4.5 $0.00002 $0.00346

Measured yesterday against content hash 6ffcb51cfff1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

developer-guidelines 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.

.agent/skills/developer-guidelines/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developers Guidelines

0. Red Flags (Anti-Rationalization)

STOP and READ THIS if you are thinking:

  • "This code is messy, I'll clean it up while I'm here" -> WRONG. You MUST change ONLY what the task requires.
  • "I'll skip the test, it's a trivial change" -> WRONG. ALL changes require verification.
  • "The reviewer didn't mention this, but I know better" -> WRONG. Fix ONLY what is requested in reviewer comments.
  • "I don't need to update .AGENTS.md for such a small change" -> WRONG. Update .AGENTS.md for touched source scopes under memory tracking policy.
  • "I'll restructure the module layout / add a new service / change the public API" -> STOP. Architectural changes must be raised, not silently introduced. Implementation patterns within your scope are fine.
  • "I'll add this feature/endpoint/config just in case" -> WRONG. Speculative features are prohibited. Build what was asked.

1. Strict Adherence

  • Follow Instructions: Execute the task EXACTLY as described.
  • No Unsolicited Changes: NEVER refactor code or add features not explicitly requested.
  • Scope Control: LEAVE unrelated code unchanged, even if it looks "bad" (unless it blocks your task).
  • Task Traceability: Every change must serve the current task. Professional implementation choices (refactoring touched code, adding appropriate error handling) are OK. Unrelated drive-by changes to code you didn't need to touch are NOT.
  • Style Matching: Match existing code style (quotes, type hints, spacing, boolean patterns) even if you'd do it differently.

1.5 Think Before Implementing

  • Surface Assumptions: Before coding any non-trivial change, state key assumptions explicitly (in chat or in TASK.md Open Questions).
  • Ambiguity Handling (graduated):
    • Critical ambiguity (affects architecture, user-facing behavior, data model): Record in TASK.md as Open Question. Ask user only if blocking.
    • Implementation ambiguity (pattern choice, internal structure): Apply professional judgment. Document the choice briefly.
    • Trivial ambiguity (naming, formatting): Just decide. Don't ask.
  • Push Back: If you see a better approach than what was requested, explain why before you start coding. This applies to task interpretation, NOT to deviating from an already-approved plan or reviewer feedback (§1 Strict Adherence still governs execution).

Read the full file on GitHub · 197 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 · 197 lines · 23 tokens per session scan A 6ffcb51cfff1

Subscribe to this mod's changes

developer-guidelines is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 18d ago), licensed Apache-2.0. It adds 23 tokens to every session and 3,461 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

add-tests

Generates tests for existing code. Analyzes the target function, method, or class to identify the happy path, error cases, and edge cases, then writes test cases following the project's testing framework and naming conventions. Invoked when the user asks to add tests, write tests, cover code, or increase coverage.

soulcodex/agentic · 67 tokens

oracle

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

the-open-agent/openagent · 25 tokens

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens

company-hiring-intelligence

Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…

tinyfish-io/tinyfish-cookbook · 169 tokens

Swift Performance Optimization Skill

Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…

termio-sh/termio · 68 tokens

loop-engineering

Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).

huytieu/COG-second-brain · 63 tokens