agentmods.dev

llm-cli-gateway: Skill for Claude Code

.agents/skills/provider-devin/SKILL.md

provider-devin is a skill for Claude Code, Codex from verivus-oss/llm-cli-gateway. It costs 68 tokens per session (1,456 once invoked), scanned B, original, MIT.

A maintenance guide for keeping a gateway's Devin CLI integration aligned with the upstream command-line tool. Devin is an AI coding service, and a CLI is a text-based program interface.

In plain words
What is it for?
Use it when Devin releases CLI changes or when checking whether the gateway still matches Devin's documented interface.
Why use it?
It helps prevent the gateway from using outdated Devin flags, commands, permission modes, or connection settings.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is verivus-oss/llm-cli-gateway's own configuration. It tells Claude Code and Codex how to work on llm-cli-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-cli-gateway configures →

Part of the llm-gateway plugin — 24 skills, 4 commands, 2 MCP servers shipped together

not rated 15repo changed 4d ago B scan 68 tokens original MIT
View source ↗ verivus-oss/llm-cli-gateway llm-cli-gateway.dev
Reuse

Borrowing it

Nothing to install: this file belongs to verivus-oss/llm-cli-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/verivus-oss/llm-cli-gateway/main/.agents/skills/provider-devin/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/verivus-oss/llm-cli-gateway

Made for: Claude Code, Codex.

Or install llm-gateway, the plugin that ships this one along with the rest of its 24 skills, 4 commands, 2 MCP servers.

Wrote 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.

agentmods badge for provider-devin

README.md
[![agentmods](https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/provider-devin.svg)](https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/provider-devin)
Your own site
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/provider-devin"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/provider-devin.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01456
Opus 5 $0.00034 $0.00728
Sonnet 5 $0.00014 $0.00291
Haiku 4.5 $0.00007 $0.00146

Measured 4d ago against content hash 1e80c48c5ab6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

provider-devin 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 4d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

8. Devin's CLI print prompt is argv-bound. Oversized UTF-8 input fails before
.agents/skills/provider-devin/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Provider: Devin CLI

Keep the gateway's Devin (devin) integration aligned with the upstream CLI. This skill does not define argv or environment behaviour. The single mechanical source of truth is UPSTREAM_CLI_CONTRACTS.devin in src/upstream-contracts.ts, enforced by validateUpstreamCliArgs and validateUpstreamCliEnv. Do not re-encode flags, permission modes, ACP rules, or session rules here or in TOML.

Identity

Field Value
CliType devin
Executable devin
Distribution vendor installer / self-update
Command docs https://cli.devin.ai/docs/reference/commands
CLI docs https://docs.devin.ai/cli
Changelog https://docs.devin.ai/cli/changelog/stable
Watch categories flags, subcommands, permission-modes, acp-entrypoint

These values mirror UPSTREAM_CLI_CONTRACTS.devin.upstreamMetadata and docs/upstream/provider-sources.dag.toml ([providers.devin]). The TypeScript metadata is authoritative; the TOML is scanner input only.

Gateway use

  1. Discover the live gateway surface before relying on Devin-specific controls: 
    provider_tool_capabilities({cli:"devin"})
    For a cached read-only resource, use provider-tools://devin.
  2. Use devin_request for normal work and devin_request_async for long-running work. Sync calls may auto-defer; poll llm_job_status and fetch with llm_job_result when that happens.
  3. Omit model unless the caller explicitly requests one. Use only request controls reported by provider_tool_capabilities. Devin must use approvalStrategy:"legacy": it rejects Claude-only mcp_managed before launch, and approvalPolicy has no effect.
  4. Treat permissionMode:"accept-edits" as an explicit edit-authorizing choice. It is not equivalent to unrestricted autonomous execution.
  5. Devin accepts flat prompt only, not promptParts. For CLI transport, pass local workingDir or a verified registered workspace to bind the repository. Use gateway worktree only with an explicit provider-native sessionId that is not overridden by createNewSession; fresh, createNewSession, and resumeLatest-only worktree requests fail closed. ACP rejects workingDir and worktree; use its registered workspace selector. An unscoped CLI child runs in a fresh neutral temporary cwd, not the gateway repository.
  6. Use a real resumable provider session only when the response reports it as resumable. Gateway bookkeeping IDs are not automatically valid Devin session IDs. resumeLatest:true needs workingDir, workspace, or a configured default workspace because Devin's latest-session pointer is cwd-scoped.
  7. Native ACP is capability-gated. It rejects approvalStrategy:"mcp_managed" and any approvalPolicy, as does the Devin CLI gateway path. Probe the actual entrypoint with devin acp --help, not only devin --version.
  8. Devin's CLI print prompt is argv-bound. Oversized UTF-8 input fails before spawn as non-retryable input_too_large; the gateway never truncates it. All other caller-controlled argv values are admitted in their final encoded form before spawn. Embedded NUL bytes return non-retryable invalid_input without exposing the rejected value.

Read the full file on GitHub · 119 lines

Files

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.

Changes

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.

  1. 4d ago Changed 1e80c48c5ab6
  2. 8d ago First seen · 119 lines · 68 tokens per session scan B 78216ebe9d76

Subscribe to this mod's changes

provider-devin is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,456 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsClaude CodeLLMcodexgemini-cligrokmcp
Related

Other skills, from other repositories

provider-integration

Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…

hex/claude-council · 74 tokens

architect

System design, tradeoffs, and complex technical decisions.

antonbabenko/deliberation · 13 tokens

security-analyst

Threat-model and find vulnerabilities, with practical remediation.

antonbabenko/deliberation · 15 tokens

plan-reviewer

Validate that a work plan is executable before work starts.

antonbabenko/deliberation · 15 tokens

researcher

Research external libraries, APIs, and best practices, with evidence.

antonbabenko/deliberation · 16 tokens

debugger

Rank root-cause hypotheses and propose the smallest safe fix.

antonbabenko/deliberation · 15 tokens