AgentScope Java is a framework for building distributed software agents that use language models to perform tasks over extended sessions. It is intended for enterprise applications needing agent coordination, controlled tool use, isolated workspaces, event streaming, and distributed session management. The catalogue entries provide skills and instructions for working with this framework.
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 agentscope-ai/agentscope-java --skill git-checkpointgit clone --depth 1 https://github.com/agentscope-ai/agentscope-javaWrote 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/agentscope-ai/agentscope-java/git-checkpoint)<a href="https://agentmods.dev/skills/agentscope-ai/agentscope-java/git-checkpoint"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentscope-java/git-checkpoint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentscope-ai/agentscope-java/git-checkpoint"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentscope-java/git-checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 16 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 27 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 28 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00039 | $0.00291 |
| Opus 5.5 | $0.00016 | $0.00116 |
| Sonnet 5.5 | $0.00008 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
git-checkpoint 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 1mo 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.
What it actually says
Git Checkpoint and Rollback
You work in a git-backed sandbox. Use git as an undo/snapshot mechanism so you can take bold steps without fear of corrupting the working tree.
Checkpoint before risky work
Before a large refactor or anything you are unsure about, save the current good state:
git add -A && git commit -m "checkpoint: before <short description>" --no-verify
Record the commit hash (git rev-parse HEAD) so you can return to it.
Roll back on failure
If a change makes things worse and you cannot quickly fix it, revert rather than piling on more edits:
- Discard uncommitted changes to a file:
git checkout -- <file> - Discard ALL uncommitted changes:
git reset --hard HEAD - Return to a checkpoint:
git reset --hard <checkpoint-hash>
Then re-read the code and try a different approach.
Rules
- NEVER create
.bak/ backup files — git is your history. - Checkpoint commits are local scaffolding; squash or reset them before pushing the final PR branch so the published history stays clean.
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.
- 1mo ago First seen · 37 lines · 39 tokens per session scan A 26aa9060bd2e
git-checkpoint is a skill published in the GitHub repository agentscope-ai/agentscope-java (6,013 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 291 once invoked, about $0.0002 per session on Opus 5.5. 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
Codex
Guides operator-owned delegation to Codex when the task fits a bounded coding lane, review pass, or worktree-isolated implementation track.
GitHub Issues
Triage GitHub issues, extract the real ask, and connect each issue to the relevant files, tests, or release surface before acting.
GitHub PR Workflow
Move cleanly through branch, diff, review, validation, and PR update steps without losing scope or repository-native workflow.
GitHub Repo Management
Inspect repository metadata, branches, permissions, and operational state before changing settings or branch structure.
commit
Create git commits with good messages. Use when user says "commit", "create commit", or asks to commit changes.
public-plugin-packaging
Use when packaging an Agentlas agent repo for public GitHub release, Codex plugin submission, Claude adapter distribution, or one-line terminal installation.