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/suge8/bao/coding-agentnpx skills add Suge8/Bao --skill coding-agentgit clone --depth 1 https://github.com/Suge8/BaoWhat 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 | $0.00016 | $0.02274 |
| Opus 5 | $0.00008 | $0.01137 |
| Sonnet 5 | $0.00003 | $0.00455 |
| Haiku 4.5 | $0.00002 | $0.00227 |
Grade A, and why
coding-agent 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Agent Skill
Delegate programming tasks to AI coding agents through the unified coding_agent tool. The tool routes to whichever backend is installed: OpenCode (opencode), Codex (codex), or Claude Code (claudecode). All backends share the same parameter interface, with a few backend-specific extras. Session continuity is backend-scoped: each backend keeps its own per-chat session chain.
When to Use
Use coding_agent when the user asks to:
- Write, refactor, debug, or fix code
- Add features, create modules, scaffold components
- Run tests and fix failures
- Perform multi-file code changes across a project
- Git operations (commits, branches, PRs) via natural language
Do NOT use when:
- The user asks a conceptual question about code (answer directly)
- A single file read suffices (use
read_file) - A single shell command is needed (use
exec) - The task has nothing to do with programming
Tool Parameters
coding_agent
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
agent |
string | yes | — | Backend: "opencode", "codex", or "claudecode" |
prompt |
string | yes | — | Task description. Be specific, reference files. |
project_path |
string | no | workspace | Project directory to operate in. |
session_id |
string | no | — | Explicit session ID to continue. |
continue_session |
boolean | no | true | Auto-resume the previous session for this chat on the selected backend. |
model |
string | no | — | Override model (e.g. anthropic/claude-sonnet-4-20250514, o4-mini). |
timeout_seconds |
integer | no | 1800 | Optional execution timeout. Usually omit this and use the 30-minute default. Range: 30–1800. |
response_format |
string | no | hybrid |
Output format: hybrid, json, or text. |
max_retries |
integer | no | 1 | Reserved compatibility field. Hidden automatic retries are disabled. Range: 0–2. |
max_output_chars |
integer | no | 4000 | Max chars for stdout/stderr. Range: 200–50000. |
include_details |
boolean | no | false | Include full stdout/stderr inline. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 185 lines · 16 tokens per session scan A 49f5c8295885
coding-agent is a skill published in the GitHub repository Suge8/Bao (23 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 2,274 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 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…