coding-agent-builder

coding-agent-builder is a skill for Claude Code, Codex from khalilbenaz/claude-skills-collection. It costs 88 tokens per session (2,207 once invoked), scanned A, original, MIT.

A guide for building autonomous coding agents: software that can read, change, and test code. It covers single-agent and multi-agent designs, where separate agents may plan, implement, and review work.

In plain words
What is it for?
Designing agents that edit files, run commands, use Git, and run automated tests in an IDE, CI/CD pipeline, or coding workflow.
Why use it?
It helps turn a broad idea for an AI programmer into a defined system with clear tools and responsibilities. It also helps choose a design suited to the size and complexity of the task.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: mentions Claude Code; built for aider.

Good fit Designing agents that edit files, run commands, use Git, and run automated tests in an IDE, CI/CD pipeline, or coding workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/khalilbenaz/claude-skills-collection/coding-agent-builder
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.

Any agent
npx skills add khalilbenaz/claude-skills-collection --skill coding-agent-builder
Clone the repo
git clone --depth 1 https://github.com/khalilbenaz/claude-skills-collection

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for coding-agent-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/coding-agent-builder/github.svg)](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/coding-agent-builder)
Your own site
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/coding-agent-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/coding-agent-builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for coding-agent-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/coding-agent-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/coding-agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,207 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 39
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium MCP Rug Pull · line 52
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
How audits are shown
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 5.1 $0.00088 $0.02207
Opus 5 $0.00044 $0.01104
Sonnet 5 $0.00018 $0.00441
Haiku 4.5 $0.00009 $0.00221

Measured 9d ago against content hash 9b5995f89d7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

coding-agent-builder scanned grade A with 1 finding 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 9d ago.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

r = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=timeout)
agent-skills/coding-agent-builder/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Agent Builder

Quand utiliser ce skill

Conception ou implémentation d'un agent autonome qui interagit avec une base de code : lecture/écriture de fichiers, exécution de commandes, gestion Git, tests automatisés. S'applique à un agent SWE-bench-style, un assistant intégré dans un IDE, ou un pipeline CI/CD.

Critères d'architecture : mono-agent vs multi-agents

Critère Mono-agent Multi-agents (planner + executor + reviewer)
Tâche simple (<5 fichiers) Surcharge inutile
Tâche complexe, multi-modules ❌ fragile
Budget tokens serré
Cohérence inter-fichiers critique

Workflow en 10 étapes

1. Définir les tools fondamentaux

Chaque tool renvoie un dict structuré (stdout, stderr, exit code). Pas d'exception silencieuse.

import subprocess, pathlib

def read_file(path: str) -> dict:
    p = pathlib.Path(path)
    return {"content": p.read_text(encoding="utf-8"), "exists": p.exists()}

def write_file(path: str, content: str) -> dict:
    pathlib.Path(path).write_text(content, encoding="utf-8")
    return {"written": True, "path": path}

def run_command(cmd: str, timeout: int = 30) -> dict:
    r = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=timeout)
    return {"stdout": r.stdout, "stderr": r.stderr, "returncode": r.returncode}

def run_tests(suite: str = ".") -> dict:
    return run_command(f"pytest {suite} --tb=short -q")

Outils minimaux requis : read_file, write_file, run_command, search_code, git_diff, run_tests.

2. Sandbox d'exécution (obligatoire en production)

Docker (auto-hébergé) :

docker run --rm \
  --network=none \          # pas d'accès réseau
  --memory=512m \
  --cpus=1 \
  --read-only \
  -v $(pwd)/workspace:/workspace \
  python:3.12-slim \
  bash -c "cd /workspace && python agent_task.py"

E2B (sandbox managé, plus simple) :

from e2b_code_interpreter import Sandbox
with Sandbox() as sbx:
    result = sbx.run_code("print('hello')")
    print(result.text)

Read the full file on GitHub · 228 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. 9d ago First seen · 228 lines · 88 tokens per session scan A 9b5995f89d7b

Subscribe to this mod's changes

coding-agent-builder is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 15d ago), licensed MIT. It adds 88 tokens to every session and 2,207 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

explain

Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.

softspark/ai-toolkit · 34 tokens

common-sense-index-investing-bogle

Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.

simbajigege/book2skills · 38 tokens

finance-econ-literacy

A Korean-language guide to understanding economic indicators such as interest rates, exchange rates, inflation, GDP, employment, and trade. It explains how these figures can affect loans, savings, investments, and spending.

modu-ai/moai-cowork · 128 tokens

stock-analysis-lead

Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…

johnqtcg/awesome-skills · 229 tokens

stock-business-review

Review a US-listed company's business model and revenue structure for an equity-research workup. Covers product/service mix, customer concentration, geographic exposure, industry position, revenue-growth decomposition (organic vs acquired vs price vs volume), and information-tier discipline (which numbers are facts vs…

johnqtcg/awesome-skills · 121 tokens

stock-earnings-quality-review

Review a US-listed company's earnings quality, cash-flow integrity, and operating leverage for an equity-research workup. Covers operating cash flow vs net income drift, free cash flow trajectory, capex character (maintenance vs expansion), equity issuance / shareholder-return yield, revenue-quality signals…

johnqtcg/awesome-skills · 147 tokens