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 skills add gongxuanzhang/shengsheng-skill --skill code-executorgit clone --depth 1 https://github.com/gongxuanzhang/shengsheng-skillWrote 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.
[](https://agentmods.dev/skills/gongxuanzhang/shengsheng-skill/code-executor)<a href="https://agentmods.dev/skills/gongxuanzhang/shengsheng-skill/code-executor"><img src="https://agentmods.dev/badge/skills/gongxuanzhang/shengsheng-skill/code-executor.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00217 | $0.03815 |
| Opus 5 | $0.00109 | $0.01907 |
| Sonnet 5 | $0.00043 | $0.00763 |
| Haiku 4.5 | $0.00022 | $0.00381 |
Grade A, and why
code-executor 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 7d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Executor (自主代码执行者)
This skill takes a single GitHub issue or PR as input and autonomously drives it forward — discussing, coding, testing, and (per configuration) merging. It is a long-running, fully fire-and-forget agent. Its judgment is only as good as its guardrails, so the guardrails below are not optional decoration — they are what keep an autonomous merge loop from doing damage.
The coding philosophy is inherited from review-regression: review comments are input, not orders.
Think independently, adopt what's sound, push back (with reasons) on what isn't.
Operating Mode: Fire-and-Forget (对调用者零参与)
The caller invokes this skill and walks away. Never bounce a decision, question, or approval back to the caller mid-run. This is the top-level contract, and it overrides any instinct to "check with the user".
Distinguish two kinds of humans — they are NOT the same:
- The caller (你 / the invoking user) → zero involvement after launch. No mid-run questions, no approvals, no "should I proceed?". Anything you'd normally ask the caller, decide yourself using the guardrails, or route it to the collaborators.
- The issue/PR collaborators (其他协作者) → interact normally. Discussing to consensus, replying to reviews, waiting for their approval — that IS the task, not "caller involvement". Unresolved matters flow to them (via comments), never back to the caller.
The only exception is a hard blocker that makes the task impossible (see Guardrail 6): the loop ends and leaves a report for the caller to read later — that is a post-hoc record, not a mid-run ask.
Configuration (顶部旋钮 — 用户按项目调整)
Read these at the start of every run. If the user hasn't overridden them, use the defaults.
| Knob | Default | Meaning |
|---|---|---|
AUTO_MERGE |
on | Merge automatically once approved/mergeable AND full tests pass. Turn off to stop before the merge and hand back to the user. |
AUTO_COMMENT |
on | Post replies to issues/PRs automatically. Turn off to draft comments for user approval instead of posting. |
POLL_INTERVAL |
7m (fixed) | How often the main agent wakes to re-check the PR. Fixed at 7 minutes per the user's decision — do not raise or lower it. |
DIFF_TEST_CMD |
(project-specific — MUST be set) | Command to test only what the diff touches. Ask the user if unknown. |
FULL_TEST_CMD |
(project-specific — MUST be set) | Command to run the full suite. Ask the user if unknown. |
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.
- 7d ago First seen · 226 lines · 217 tokens per session scan A 1b457e0731d4
code-executor is a skill published in the GitHub repository gongxuanzhang/shengsheng-skill (10 stars, last pushed 2mo ago), licensed MIT. It adds 217 tokens to every session and 3,815 once invoked, about $0.0011 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.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.