agentleFS
Sign inStart free
SuperInstanceSuperInstance/flux-fleet-scanner/skills/coding-agent/SKILL.md

coding-agent

Skill1 starsChanged 7 months agoMITView on GitHub

Coding workflow with planning, implementation, verification, and testing for clean software development.

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create on first use: mkdir -p ~/code

    line 24
  2. Very specific:

    Read ~/code/memory.md for user's stated preferences if it exists.

    line 54
  3. Distinctive:

    Only store what user explicitly asks to save.

    line 79
  4. Distinctive:

    Only preferences user explicitly asks to save

    line 109

“Common” is measured: kept by at least 6 in 10 of the 38 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

When to Use

User explicitly requests code implementation. Agent provides planning, execution guidance, and verification workflows.

Architecture

User preferences stored in ~/code/ when user explicitly requests.

~/code/
  - memory.md    # User-provided preferences only

Create on first use: mkdir -p ~/code

Quick Reference

TopicFile
Memory setupmemory-template.md
Task breakdownplanning.md
Execution flowexecution.md
Verificationverification.md
Multi-task statestate.md
User criteriacriteria.md

Scope

This skill ONLY:

  • Provides coding workflow guidance
  • Stores preferences user explicitly provides in ~/code/
  • Reads included reference files

This skill NEVER:

  • Executes code automatically
  • Makes network requests
  • Accesses files outside ~/code/ and the user's project
  • Modifies its own SKILL.md or auxiliary files
  • Takes autonomous action without user awareness

Core Rules

1. Check Memory First

Read ~/code/memory.md for user's stated preferences if it exists.

2. User Controls Execution

  • This skill provides GUIDANCE, not autonomous execution
  • User decides when to proceed to next step
  • Sub-agent delegation requires user's explicit request

3. Plan Before Code

  • Break requests into testable steps
  • Each step independently verifiable
  • See planning.md for patterns

4. Verify Everything

AfterDo
Each functionSuggest running tests
UI changesSuggest taking screenshot
Before deliverySuggest full test suite

5. Store Preferences on Request

User saysAction
"Remember I prefer X"Add to memory.md
"Never do Y again"Add to memory.md Never section

Only store what user explicitly asks to save.

Workflow

Request -> Plan -> Execute -> Verify -> Deliver

Common Traps

  • Delivering untested code -> always verify first
  • Huge PRs -> break into testable chunks
  • Ignoring preferences -> check memory.md first

Self-Modification

This skill NEVER modifies its own SKILL.md or auxiliary files. User data stored only in ~/code/memory.md after explicit request.

External Endpoints

This skill makes NO network requests.

EndpointData SentPurpose
NoneNoneN/A

Security & Privacy

Data that stays local:

  • Only preferences user explicitly asks to save
  • Stored in ~/code/memory.md

Data that leaves your machine:

  • None. This skill makes no network requests.

This skill does NOT:

  • Execute code automatically
  • Access network or external services
  • Access files outside ~/code/ and user's project
  • Take autonomous actions without user awareness
  • Delegate to sub-agents without user's explicit request

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free