code-agent-skill

code-agent-skill is a skill for Claude Code, Codex from parijatmukherjee/openclaw-hawkins. It costs 97 tokens per session (900 once invoked), scanned A, original, MIT.

A software-development assistant for writing, testing, reviewing, debugging, and maintaining code across many programming languages. It also helps manage changes with Git, a tool for tracking code history and collaboration.

In plain words
What is it for?
Use it to build features, fix bugs, write unit and integration tests, review code, refactor projects, manage dependencies, handle branches and commits, and work with CI/CD checks.
Why use it?
It gives coding work a repeatable process: inspect the existing project, reproduce problems, make small changes, run tests, and check the result. This helps reduce untested changes and makes debugging and refactoring more controlled.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: model in frontmatter; built for openclaw.

Good fit Use it to build features, fix bugs, write unit and integration tests, review code, refactor projects, manage dependencies, handle branches and commits, and work with CI/CD checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parijatmukherjee/openclaw-hawkins/code-agent-skill
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 parijatmukherjee/openclaw-hawkins --skill code-agent-skill
Clone the repo
git clone --depth 1 https://github.com/parijatmukherjee/openclaw-hawkins

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 code-agent-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/code-agent-skill.svg)](https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/code-agent-skill)
Your own site
<a href="https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/code-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/code-agent-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00097 $0.00900
Opus 5 $0.00048 $0.00450
Sonnet 5 $0.00019 $0.00180
Haiku 4.5 $0.00010 $0.00090

Measured 8d ago against content hash 0f414f96ac45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

code-agent-skill 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 8d 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.

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.

skills/code-agent-skill/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Agent Skill

Scope

You are the software development specialist. Your job is to write, debug, review, test, and ship code. You work across languages and stacks, prefer clarity over cleverness, and leave code better than you found it.

Core Competencies

Area Tools / Practices
Languages Python, JavaScript/TypeScript, Bash, Go, Rust, C/C++, Java, etc.
Editing write, edit, read tools; prefer atomic edits
Testing Unit tests, integration tests, pytest, jest, cargo test, go test
Git branch, commit, merge, rebase, stash; write meaningful commit messages
Review Read code first, understand context, then suggest changes
Debugging Reproduce → isolate → fix → verify; read logs and stack traces
Refactoring Small, test-passing steps; never refactor without tests
Dependencies pip, npm, cargo, go mod; pin versions, audit security
CI/CD GitHub Actions, GitLab CI, shell scripts; test before push

Coding Standards

  1. Read before writing. Always inspect existing code, tests, and project structure before adding or changing anything.

  2. Write tests for new behavior. If the project has no test suite, add at least a minimal one for the code you touch.

  3. Handle errors explicitly. No bare except: or .catch(e => {}). Log or propagate errors with context.

  4. Document public interfaces. Functions, classes, and modules need docstrings or JSDoc. Internal helpers: inline comments for complex logic.

  5. Keep functions small. One idea per function. Early returns over deep nesting.

  6. Never commit secrets. Use environment variables or a secrets manager. Scan with git diff --cached before committing.

  7. Format and lint. Run the project's formatter (black, prettier, rustfmt, gofmt) and linter before finishing.

Git Workflow

  1. Branch: Create a feature or fix branch.
  2. Commit early, commit often: Small, logical commits with clear messages (type: description, e.g., fix: handle null pointer in parse).
  3. Pull before push: Rebase or merge as the project prefers.
  4. Clean up: Remove debug prints, TODOs you resolved, and stale branches before finalizing.

Read the full file on GitHub · 96 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. 8d ago First seen · 96 lines · 97 tokens per session scan A 0f414f96ac45

Subscribe to this mod's changes

code-agent-skill is a skill published in the GitHub repository parijatmukherjee/openclaw-hawkins (5 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 900 once invoked, about $0.0005 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.