Agent skill · Audited from source
async-repl-protocol
skill · parcadei/continuous-claude-v3MIT licenceAudited 28 Oct 2026 · source 79ffdab59d4c
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 79ffdab59d4c and found no filesystem, network or shell access and no hard-coded secrets. What it does: Async REPL Protocol
Cite
Cite this page
ModelsAtlas. “async-repl-protocol (parcadei/continuous-claude-v3)”. Retrieved 28 Oct 2026. https://modelsatlas.com/skills/parcadei/async-repl-protocol
Trust audit
Audit 0.4.1 · source read 28 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 1 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (1)
MEDIUMInventory / provenanceinv.symlink · .claude/scripts/mcp
.claude/scripts/mcp
- Why
- link not followed
- Fix
- —
Audit 0.4.1 · source sha 79ffdab59d4c · 28 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherparcadei GitHub userOwner of the repository this skill is read from
- Source folderparcadei/continuous-claude-v3/.claude/skills/async-repl-protocolThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict79ffdab59d4cA new audit runs when the source changes
- Repository statusNot archivedLast push 274 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Async REPL Protocol
---
name: async-repl-protocol
description: Async REPL Protocol
user-invocable: false
---
# Async REPL Protocol
When working with Agentica's async REPL harness for testing.
## Rules
### 1. Use `await` for Future-returning tools
```python
content = await view_file(path) # NOT view_file(path)
answer = await ask_memory("...")
```
### 2. Single code block per response
Compute AND return in ONE block. Multiple blocks means only first executes.
```python
# GOOD: Single block
content = await view_file(path)
return any(c.isdigit() for c in content)
# BAD: Split blocks (second block never runs)
content = await view_file(path)Excerpt, first 633 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 79ffdab
git clone https://github.com/parcadei/continuous-claude-v3 git -C continuous-claude-v3 checkout 79ffdab59d4c
The author documents no install command, so this uses the repository directly. Our verdict covers commit 79ffdab59d4c only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
79ffdab59d4c
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/parcadei/async-repl-protocol/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
parcadei/continuous-claude-v3
Reference guide for Agentica multi-agent infrastructure APIs
parcadei/continuous-claude-v3
Agent Context Isolation
parcadei/continuous-claude-v3
Agent Orchestration Rules
parcadei/continuous-claude-v3
Agentic Workflow Pattern
parcadei/continuous-claude-v3
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
parcadei/continuous-claude-v3
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Add this badge to your README
[](https://modelsatlas.com/skills/parcadei/async-repl-protocol/)
<a href="https://modelsatlas.com/skills/parcadei/async-repl-protocol/"><img src="https://modelsatlas.com/skills/parcadei/async-repl-protocol/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about async-repl-protocol
What does the async-repl-protocol skill do?
Is async-repl-protocol safe to install?
What can async-repl-protocol access on my machine?
How current is this page?
Sources
- github.com/parcadei/continuous-claude-v3/tree/main/.claude/skill — the audited source at commit 79ffdab59d4c and every finding aboveObserved · 28 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the async-repl-protocol skill do?
- Is async-repl-protocol safe to install?
- What can async-repl-protocol access on my machine?