coding-agent

A tool for handing coding work to Codex, Claude Code, or Pi agents that run in the background.

In plain words
What is it for?
Building features or apps, reviewing pull requests in a temporary directory, refactoring large codebases, and exploring files during iterative coding work.
Why use it?
It helps when a task is too large or involved to handle as a quick edit in the current session.

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/safeai-lab-x/clawkeeper/coding-agent
Any agent
npx skills add SafeAI-Lab-X/ClawKeeper --skill coding-agent
Clone the repo
git clone --depth 1 https://github.com/SafeAI-Lab-X/ClawKeeper

Made for: Claude Code, Codex.

Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,748 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.00157 $0.02748
Opus 5 $0.00078 $0.01374
Sonnet 5 $0.00031 $0.00550
Haiku 4.5 $0.00016 $0.00275

Measured 2d ago against content hash c2db324a6adf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

coding-agent scanned grade B 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Model:** `gpt-5.2-codex` is the default (set in ~/.codex/config.toml)
legacy/clawkeeper-watcher/skills/coding-agent/SKILL.md · 296 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2d ago First seen · 296 lines · 157 tokens per session scan B c2db324a6adf

Subscribe to this mod's changes

coding-agent is a skill published in the GitHub repository SafeAI-Lab-X/ClawKeeper (1,023 stars, last pushed 16d ago), with no licence file. It adds 157 tokens to every session and 2,748 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

swarmclaw

AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.

swarmclawai/swarmclaw · 67 tokens

send-to-minion

Use this skill only when the user explicitly invokes $send-to-minion, /send-to-minion, or explicitly asks to delegate a prompt to one minion, helper, worker, child agent, spawned agent, subagent, Claude Code agent, or other single delegated agent. It sends the user's prompt to exactly one subagent using the current…

bastos/skills · 104 tokens

validate-structured-model-output

Validates JSON or tool-call model outputs without repair, separating parse, schema, supplied-identifier, semantic, replay, and safety failures. Use for first-attempt benchmarks, teacher-label pipelines, and bounded model tool selection.

bastos/skills · 51 tokens

unhobble-agent-context

Audits and designs lean, coherent context across system prompts, persistent instructions, repository guidance, skills, tool descriptions, memory, and references. Use for context engineering; creating, reviewing, simplifying, or reorganizing agent context; resolving conflicting, duplicated, bloated, stale, or misplaced…

bastos/skills · 77 tokens

design-resumable-model-evaluation

Designs strict model benchmarks that persist per-case evidence, resume without repeating completed work, separate first-attempt behavior from remediation, and stop early only when failure is mathematically certain. Use for slow, costly, or interruptible evaluations.

bastos/skills · 55 tokens

team-up

Orchestrate persistent agent teams with TeamCreate. Use when the user says "team up", "spin up a team", or invokes /team-up.

nvandessel/team-up · 34 tokens