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.
npx agentmods add skills/understudy-ai/understudy/coding-agentnpx skills add understudy-ai/understudy --skill coding-agentgit clone --depth 1 https://github.com/understudy-ai/understudyWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00160 | $0.02730 |
| Opus 5 | $0.00080 | $0.01365 |
| Sonnet 5 | $0.00032 | $0.00546 |
| Haiku 4.5 | $0.00016 | $0.00273 |
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 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.
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) This is a copy
75% identical to coding-agent — 95 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Agent (bash-first)
Use bash (with optional background mode) for all coding agent work. Simple and effective.
⚠️ PTY Mode: Codex/Pi/OpenCode yes, Claude Code no
For Codex, Pi, and OpenCode, PTY is still required (interactive terminal apps):
# ✅ Correct for Codex/Pi/OpenCode
bash pty:true command:"codex exec 'Your prompt'"
For Claude Code (claude CLI), use --print --permission-mode bypassPermissions instead.
--dangerously-skip-permissions with PTY can exit after the confirmation dialog.
--print mode keeps full tool access and avoids interactive confirmation:
# ✅ Correct for Claude Code (no PTY needed)
cd /path/to/project && claude --permission-mode bypassPermissions --print 'Your task'
# For background execution: use background:true on the exec tool
# ❌ Wrong for Claude Code
bash pty:true command:"claude --dangerously-skip-permissions 'task'"
Bash Tool Parameters
| Parameter | Type | Description |
|---|---|---|
command |
string | The shell command to run |
pty |
boolean | Use for coding agents! Allocates a pseudo-terminal for interactive CLIs |
workdir |
string | Working directory (agent sees only this folder's context) |
background |
boolean | Run in background, returns sessionId for monitoring |
timeout |
number | Timeout in seconds (kills process on expiry) |
elevated |
boolean | Run on host instead of sandbox (if allowed) |
Process Tool Actions (for background sessions)
| Action | Description |
|---|---|
list |
List all running/recent sessions |
poll |
Check if session is still running |
log |
Get session output (with optional offset/limit) |
write |
Send raw data to stdin |
submit |
Send data + newline (like typing and pressing Enter) |
send-keys |
Send key tokens or hex bytes |
paste |
Paste text (with optional bracketed mode) |
kill |
Terminate the session |
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.
- yesterday First seen · 296 lines · 160 tokens per session scan B bedf22709b3f
coding-agent is a skill published in the GitHub repository understudy-ai/understudy (456 stars, last pushed 2mo ago), licensed MIT. It adds 160 tokens to every session and 2,730 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 75% identical to coding-agent, differing in 95 lines, and is treated as a copy.
Other skills, from other repositories
release-openclaw-maintainer
Prepare or verify OpenClaw stable, beta, and extended-stable releases, including backport discovery, changelogs, release notes, publish commands, and artifacts.
openclaw-testing
Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.
autoreview
Structured Codex, Claude, Amp, Pi, or Kimi code review when explicitly requested.
release-openclaw-ci
Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.
auto-qa
Continuously audit, live-test, and stress-test the current OpenClaw codebase across at least ten independently scoped subsystem lanes; default to 100 independently verified, landed root-cause fixes, maintain an evidence-backed report, and announce each merged pull request immediately. Use for OpenClaw-wide autonomous…
crabbox
Crabbox/Testbox remote proof: portable provider routing, untrusted isolation, Linux/macOS/Windows/WSL2, live E2E, diagnostics, cleanup.