devin-cli
Delegate bounded coding tasks to the local Devin CLI over ACP from a supervising agent such as Claude Code or Codex.
Skill by scarletkc
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/scarletkc-devin-cli
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building, agent-orchestration, code-generation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/devin-cli
What's inside
- Skill name
devin-cli- Description
- Delegate bounded coding tasks to the local Devin CLI over ACP from a supervising agent such as Claude Code or Codex. Use when the user asks to hand work to Devin, when an independent implementation, port, review, or investigation can run in parallel with your own work, or when an earlier Devin session needs a follow-up. Includes a blocking run helper with single-use permission answers, a deny policy, progress summaries, and session resume.
- License
- Apache-2.0
- Metadata
- author: scarletkc · source: https://github.com/scarletkc/agents · summary: Hand bounded tasks to Devin CLI over ACP, keep its permissions single-use, watch progress, and resume the same session for follow-ups.
- Instructions
- 136 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (3)
- SKILL.md
- protocol.md · references/
- devin_acp.py · scripts/
SKILL.md (first lines)
# Devin CLI Devin CLI is a separate coding agent on the same machine. `devin acp` speaks the Agent Client Protocol over stdio; the bundled helper [scripts/devin_acp.py](scripts/devin_acp.py) drives one turn, answers permission requests from a local policy, and records everything in a run directory. It uses only the Python standard library (3.10+). Resolve the script relative to this installed skill, not the project being worked on. Devin must already be installed and signed in. Signing in opens a browser, so the user does it with `devin auth login`; the helper never authenticates and never changes Devin's configuration. If `devin` is missing, signed out, or out of quota, report that and the work that remains instead of quietly doing the task yourself. ## Run a task ```sh python <script> run --cwd <absolute-workspace> --prompt-file <brief.md> [--run-dir <dir>] python <script> progress --run-dir <dir> python <script> run --cwd <absolute-workspace> --resume <session_id> --prompt-file <follow-up.md> ``` `run` blocks until Devin ends its turn, so start it with your own background facility (a background shell command, `nohup ... &`, `Start-Process`) when you have other work. It prints JSON lines: `started` with the run directory, `session` with Devin's session ID, and `finished` with the summary. It exits 0 only when the turn ended normally. Each run gets its own owner-only run directory holding `final.md` (Devin's final message), `summary.json`, `events.jsonl`, and `devin.stderr.log`; `run` refuses a directory that already holds a run. The files contain the brief and Devin's output, so keep them out of shared or tracked locations. `--help` lists every flag; [references/protocol.md](references/protocol.md) covers the ACP details. ## Write the brief Devin sees none of your conversation. A brief that works on the first try states, in this order: 1. The goal and why it matters, in a paragraph. 2. The current state: what already exists, what is committed, where. 3. Files to read first, including the project's conventions. 4. The environment: absolute paths to interpreters and tools, environment variables, and the exact commands that build, test, and validate. 5. Scope: the files or modules this task owns, and what other workers own. 6. Rules: leave changes uncommitted; no branch, stash, reset, or push; the directories it must not touch. 7. Done means: commands that must pass and numbers that must hold (for example, the test count must not drop). 8. What the final message must contain: files changed, counts, every intentional deviation, and anything left unfinished. Use a UTF-8 prompt file rather than shell-quoted text. Size each task so its "done" can be checked in one pass; split a large port into steps whose acceptance does not depend on work still in flight. ## Isolate and integrate - Give every writing task its own git worktree, created from a commit that contains what Devin needs. If the base has uncommitted work, copy it in (`git ls-files -m -o --exclude-standard` lists it; in Git Bash on Windows pass `--force-local` to `tar` so `C:` paths are not read as remote hosts). - Never let two writers edit the same files. Parallel tasks get explicit ownership lists in their briefs, and a module both need is ported first, on its own. - Devin leaves its changes uncommitted. Review them, copy them into the integration tree, and commit there. Files changed on both sides need a manual merge. - Restore or discard only named paths. `git checkout -- .` or `git reset --hard` in a tree with other uncommitted work destroys it. - Remove the worktree and its branch after integrating. ## Permissions The helper answers each request with a single-use option: `allow_once` or `reject_once`. It never selects `allow_session`, `allow_always`, `allow_always_global`, or `switch_bypass`, because those persist in Devin's configuration or change the session's mode. By default it rejects git operations that rewrite history or switch branches and worktrees, publishing through `gh`, and edit, delete, or move requests whose target is outside `--cwd` or missing. Adjust with `--deny <regex>`, `--no-default-deny`, and `--allow-write-root <dir>`. Shell commands are matched only against the deny patterns; a command can write anywhere, so no path check applies to it. For a task that must not change anything, pass `--read-only`: it rejects every edit, delete, move, and shell-command request and starts the session in `ask` mode (`plan` is also accepted). The policy only sees what Devin asks about. In `accept-edits`, Devin's usual default, it applies workspace edits and runs read-only tools without asking. Pick the mode for the job with `--mode`: `ask` answers without editing, `plan` plans first, `smart` auto-approves more, and `bypass` approves everything. Use `bypass` only when the user explicitly authorizes it. None of this is an OS sandbox; isolation comes from the worktree. `permissions_denied` in the summary lists what Devin tried outside the policy. Read it: a denial usually means the brief left a gap. ## Model and effort `--model` takes the names `devin models list` shows; many include the effort as a suffix (for example `-high`). Without it, Devin's configured default applies. The summary's `config` reports the effective `model`, `thought_level`, and `speed`; confirm them after the run. Use `--agent-type review` for Devin's code-review agent, which reads and runs shell commands but does not edit. ## Monitor `progress` reports the tool-call count, recent tool titles, the latest plan, denials, failed tools, the length of the answer streamed so far, `seconds_since_last_event`, and the summary once finished. Large tasks routinely run for an hour or more; judge a stall by `seconds_since_last_event`, not by elapsed time. `--timeout` (default 3600 seconds) cancels the turn; if Devin does not acknowledge, the helper stops its process tree. Cancelling does not undo edits already made. ## Follow-ups
From scarletkc/agents, Apache-2.0.
More from scarletkc/agents
- 0.794score
talk-like-scarletkc
scarletkc
按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本,适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔,或在翻译中保留本人语气和立场时使用,无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。
SkillAFreshness: A★ 225Claude Code +9 - 0.794score
x-content
scarletkc
为 X(Twitter)寻找值得发的素材、筛选选题、撰写和改进帖文或串,并从读者视角重读,改善吸引力、阅读连贯性和真实讨论空间。用户问 X 最近有什么可以发、想写一条有流量的帖文,或反馈 X 帖文太复杂、读不下去时使用。只调整个人语气或忠实翻译已有文本时不触发。
SkillAFreshness: A★ 225Claude Code +9 - 0.752score
grok-cli
scarletkc
Delegate bounded tasks to Grok Build from a supervising agent such as Codex.
SkillBFreshness: B★ 225Claude Code +9 - 0.748score
antigravity-cli
scarletkc
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent.
SkillBFreshness: B★ 225Claude Code +9 - 0.746score
worktree-pr
scarletkc
Decide whether a task deserves its own git worktree and, if chosen, run it end to end: branch from the integration branch rather than the current tree, keep…
SkillBFreshness: B★ 225Claude Code +9 - 0.746score
ux-writing
scarletkc
Judgment rules for user-facing text and docs: CLI and diagnostic output, error and help text, README and docs structure, code comments, titles, and generated…
SkillBFreshness: B★ 225Claude Code +9 - 0.746score
codex-cli
scarletkc
When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model…
SkillBFreshness: B★ 225Claude Code +9 - 0.746score
marketing-copy
scarletkc
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short…
SkillBFreshness: B★ 225Claude Code +9 - 0.746score
scoped-change
scarletkc
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it.
SkillBFreshness: B★ 225Claude Code +9 - 0.746score
ask-to-plan
scarletkc
Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices.
SkillBFreshness: B★ 225Claude Code +9 - 0.742score
product-writing
scarletkc
Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup…
SkillBFreshness: B★ 225Claude Code +9
Signals
- Stars
- 225
- Forks
- 12
- Open issues
- 1
- Last commit (this folder)
- Oct 18, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/scarletkc/agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from scarletkc
- 0.795score
vexor-cli
scarletkc
Semantic file discovery via `vexor`.
SkillAFreshness: A★ 246Claude Code +9 - 0.794score
x-content
scarletkc
为 X(Twitter)寻找值得发的素材、筛选选题、撰写和改进帖文或串,并从读者视角重读,改善吸引力、阅读连贯性和真实讨论空间。用户问 X 最近有什么可以发、想写一条有流量的帖文,或反馈 X 帖文太复杂、读不下去时使用。只调整个人语气或忠实翻译已有文本时不触发。
SkillAFreshness: A★ 225Claude Code +9 - 0.794score
talk-like-scarletkc
scarletkc
按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本,适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔,或在翻译中保留本人语气和立场时使用,无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。
SkillAFreshness: A★ 225Claude Code +9 - 0.770score
Vexor
scarletkc
A semantic search engine for files and code.
ConnectorAFreshness: ALocal★ 246↓ 123/wkClaude Code +5 - 0.752score
grok-cli
scarletkc
Delegate bounded tasks to Grok Build from a supervising agent such as Codex.
SkillBFreshness: B★ 225Claude Code +9 - 0.748score
antigravity-cli
scarletkc
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent.
SkillBFreshness: B★ 225Claude Code +9
Cite this page
devin-cli skill. Agent Mart. https://agentmart.dev/skills/scarletkc-devin-cli (last updated 2026-10-24)