execution-protocol

A step-by-step working protocol for coding tasks: read the codebase, try the software, investigate errors, and implement a working solution. It tells the coding agent to act before asking the user for help.

In plain words
What is it for?
Use it for implementing fixes and features, diagnosing errors, reading an unfamiliar codebase, checking existing solutions, and deciding when a problem genuinely requires user input.
Why use it?
It reduces unnecessary questions and avoids incomplete suggestions by requiring the agent to inspect the project and reproduce problems itself. It also encourages matching the project’s existing structure and dependencies.

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/subhansh-dev/agent-maxxing/execution-protocol
Any agent
npx skills add subhansh-dev/agent-maxxing --skill execution-protocol
Clone the repo
git clone --depth 1 https://github.com/subhansh-dev/agent-maxxing

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 716 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 $0.00028 $0.00716
Opus 5 $0.00014 $0.00358
Sonnet 5 $0.00006 $0.00143
Haiku 4.5 $0.00003 $0.00072

Measured yesterday against content hash d439838e9e38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execution-protocol 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.

engineering/execution-protocol/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execution Protocol — How to Actually Get Things Done

First Principle: Solve It, Don't Ask About It

Your default mode is ACTION, not QUESTIONS.

  1. Read first, act second. Before touching anything, read the codebase. All of it. Understand what exists before proposing changes.
  2. Try it yourself. Run the code. Hit the error. Read the stack trace. Fix it. Don't ask the user to debug for you.
  3. Ship working code. Don't ship "here's a skeleton, you fill in the rest." Ship something that runs.

The Problem-Solving Chain

When you hit an obstacle:

1. Can I solve this with what I know?        → Do it
2. Can I find the answer by reading code?     → Read it
3. Can I search for the answer?               → Search it
4. Can I write code to solve it?              → Write it
5. Can I break it into smaller pieces?        → Try each piece
6. Am I actually stuck?                       → THEN ask the user

Never skip to step 6.

Code Quality Rules

Before Writing Code

  • Read the existing codebase completely
  • Understand the architecture and patterns in use
  • Check what dependencies are available
  • Look for existing solutions to similar problems

While Writing Code

  • Match the existing style (don't introduce your own conventions)
  • Handle edge cases (null, empty, boundary values)
  • Add error handling (try/catch, validation)
  • Write code that's readable 6 months from now
  • Don't over-engineer (solve the actual problem, not hypothetical ones)

After Writing Code

  • Run it. Does it work?
  • Check for syntax errors
  • Verify no regressions
  • Clean up (remove console.logs, dead code, TODOs)

File Management Rules

  • Workspace is home. Write files here, not to /tmp or random paths.
  • Relative paths. Use relative paths within the workspace.
  • Don't clobber. Before overwriting a file, read it first. Preserve what's there.
  • Clean up. Remove temp files when done.

Communication Rules

Be Honest

  • "I don't know" is better than a confident wrong answer
  • "I can't do that" is better than a broken attempt
  • "Here's what I tried and why it failed" is better than silence

Read the full file on GitHub · 85 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 · 85 lines · 28 tokens per session scan A d439838e9e38

Subscribe to this mod's changes

execution-protocol is a skill published in the GitHub repository subhansh-dev/agent-maxxing (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 716 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.