devin-cli-runtime

devin-cli-runtime is a skill for Claude Code from okisdev/claude-code-fusion. It costs 19 tokens per session (2,580 once invoked), scanned B, original, MIT.

An internal command reference for the Devin companion runtime, a local helper that can start and manage delegated coding or review jobs. It lists commands for tasks, reviews, status, results, cancellation, history, setup, and model selection.

In plain words
What is it for?
It is for starting foreground or background implementation and review jobs, resuming tasks, retrieving results, checking history, cancelling work, and recording acceptance.
Why use it?
It gives the calling agent a defined interface for launching work and checking its outcome instead of relying on undocumented commands.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the devin plugin — 2 skills, 1 agent shipped together

Good fit It is for starting foreground or background implementation and review jobs, resuming tasks, retrieving results, checking history, cancelling work, and recording acceptance.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add okisdev/claude-code-fusion
Claude Code
/plugin install devin

Made for: Claude Code.

Or install devin, the plugin that ships this one along with the rest of its 2 skills, 1 agent.

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 devin-cli-runtime

README.md
[![agentmods](https://agentmods.dev/badge/skills/okisdev/claude-code-fusion/devin-cli-runtime/github.svg)](https://agentmods.dev/skills/okisdev/claude-code-fusion/devin-cli-runtime)
Your own site
<a href="https://agentmods.dev/skills/okisdev/claude-code-fusion/devin-cli-runtime"><img src="https://agentmods.dev/badge/skills/okisdev/claude-code-fusion/devin-cli-runtime/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.

agentmods 80×15 button for devin-cli-runtime

Your own site · 80×15
<a href="https://agentmods.dev/skills/okisdev/claude-code-fusion/devin-cli-runtime"><img src="https://agentmods.dev/badge/skills/okisdev/claude-code-fusion/devin-cli-runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,580 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 $0.00019 $0.02580
Opus 5.5 $0.00008 $0.01032
Sonnet 5.5 $0.00004 $0.00516
Haiku 4.5 $0.00002 $0.00258

Measured today against content hash 4b0545409e01, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

devin-cli-runtime 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 today.

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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- Project scoped `AGENTS.md`, `AGENTS.local.md`, `AGENT.md`, `.windsurfrules`, and project skills under `.devin/skills`, `.cognition/skills`, and `.agents/skills` still load. Project `.devin/config.json`, `.devin/config.
plugins/devin/skills/devin-cli-runtime/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devin runtime

Primary helper:

  • node "${CLAUDE_PLUGIN_ROOT}/scripts/devin-companion.mjs" <subcommand> [flags]

Subcommand surface:

  • task [--write] [--model <id>] [--effort <effort>] [--resume <session-id>|--resume-last|--fresh] [--background] [--cwd <dir>] [--json] [--] [prompt]
  • review [--scope <auto|working-tree|branch>] [--base <ref>] [--focus <text>] [--model <id>] [--effort <effort>] [--cwd <dir>] [--background] [--json]
  • status [job-id] [--all] [--cwd <dir>] [--json]
  • result <job-id> [--wait] [--cwd <dir>] [--json]
  • cancel <job-id> [--cwd <dir>] [--json]
  • history [--all] [--limit <n>] [--cwd <dir>] [--json]
  • models [--refresh] [--json]
  • setup [--json]
  • record-acceptance --job-id <id> --acceptance <accepted|rejected|unverified> [--reason <text>] [--failure-kind <kind>] [--source <collector|main-loop|stats>] [--accept-failed-transport] [--json]
  • transport-create and transport-discard --raw-args-token <token>
  • task-worker and review-worker are internal background workers that the helper never invokes directly.

Execution rules:

  • Slash commands stage their complete raw arguments through transport-create, one Read of the allocated empty file, Write to that same file, and a fixed --raw-args-token invocation. The token transport applies to task, review, status, history, result, cancel, and setup. Raw request bytes never enter Bash, shell arguments, environment variables, redirections, substitutions, encoded literals, or heredocs. A transport is private, bounded, validated, and consumed once. Never delete, rename, recreate, or change the permissions of the transport file; use transport-discard when Read or Write fails or when the allocated file is not empty.
  • Place every task option before the prompt, and put -- before a prompt that begins with an option shaped token. The prompt text may also arrive on stdin.
  • The companion resolves the CLI as devin on PATH, with DEVIN_BIN overriding the path. Preflight runs devin --version and every job records devinVersion and devinBuildPath.
  • The tested interval is [3000.11, 3000.12) by major and minor version. An older or unparseable build fails preflight as setup; a newer build runs and /devin:setup reports it as newer than the tested interval. The generated configuration disables background auto update.
  • Every run executes devin acp with the workspace as its working directory. The companion sends JSON-RPC initialize, session/new or session/load, the supported session/set_config_option requests, then session/prompt. The brief appears only in that prompt message. The companion never passes --cloud, --agent-type, --model, or --refusal-fallback. Permission requests receive cancelled.
  • Consult is the default mode, --write selects write mode, and review is always read only. Consult and review set ACP mode ask and allow read, grep, glob, find_file_by_name, notebook_read, and todo_write. Write sets autonomous and additionally allows edit, write, notebook_edit, exec, get_output, kill_shell, and write_to_process. A tool_call outside the mode list terminates the process group and fails as policy.
  • Consult and review deny edit and exec in the generated configuration. Write sets DEVIN_SANDBOX=true and allows Write(<cwd>/**) plus the linked worktree Git directory. The OS sandbox confines shell writes to these scopes and fails closed when it cannot start. Sensitive real home paths and Fetch(*) are denied in every mode; other home reads may remain possible.
  • Every job uses shared private HOME, XDG_DATA_HOME, XDG_STATE_HOME, and XDG_CACHE_HOME under <data>/home, and private XDG_CONFIG_HOME at <data>/runs/<job-id>/config. The shared data directory holds the CLI session database and a symbolic link to the real user credentials file; the companion never reads or copies the credential. Generated devin/config.json disables auto update, attribution, subagents, notifications, and personal imports, and devin/mcp_config.json has empty mcpServers. The child environment never inherits DEVIN_* variables.
  • Project scoped AGENTS.md, AGENTS.local.md, AGENT.md, .windsurfrules, and project skills under .devin/skills, .cognition/skills, and .agents/skills still load. Project .devin/config.json, .devin/config.local.json, .devin/mcp_config.json, and .devin/mcp_config.local.json may add permissions, hooks, MCP servers, or imports; the companion warns when they exist. Organization settings still apply. Prompts, workspace content, and results pass through Devin's backend to the serving model vendor, so never delegate secrets or credentials to this lane.
  • Fusion routed dispatches always carry --model and --effort from the routing table. A direct user call without --model uses the account default. models reads devin models list --format json, caches the family catalog for one hour, and --refresh reads it again.
  • Models are family slugs such as kimi-k3, glm-5.2, muse-wonder, and swe-2, their aliases, or variant uids. The companion matches the requested family to a usable session model option and records that option as resolvedModel. A missing catalog family fails before job creation as input; a family unavailable to the account fails as setup. Effort is the selected model's thought_level: default leaves its default, a supported level is set explicitly, and an unsupported level fails as input. speed is set to standard when offered. adaptive and fusion-* pairings are refused as input.
  • The _cognition.ai/agent_stopped or _cognition.ai/turn_stats event reports the serving model as observedModel; a difference from the selected display name renders model_mismatch without changing the transport outcome. billingPool is first-party for swe-* models and api for every other family.
  • ACP stdout carries JSON-RPC responses, session/update, permission requests, and Cognition notifications. The companion appends message chunks only after the prompt is sent, verifies request ids and the session id, and requires a prompt result with stopReason: "end_turn" and an agent stopped cause of complete for success. It records usage exactly as reported, without filling absent cache tokens or reporting cost. Malformed lines or an exit before the prompt result fail as protocol.
  • The native CLI starts in its own process group. After the prompt result, the companion closes stdin and waits up to DEVIN_COMPANION_EXIT_GRACE_MS (default 15000) before terminating the group and recording late_close. The run timeout is DEVIN_COMPANION_TIMEOUT_MS (default 540000). DEVIN_COMPANION_WAIT_TIMEOUT_MS, DEVIN_COMPANION_WAIT_POLL_MS, and DEVIN_COMPANION_PIDLESS_RUNNING_GRACE_MS use the companion defaults.
  • Ordinary delegations use one foreground helper call with timeout 600000. Only an explicit incoming user --background detaches a task or review into an internal worker and creates a manual receipt; the helper prints the job id plus /devin:status and /devin:result hints. Never add --background because a task appears large or slow, and never use Bash background mode. result --wait blocks while a job is running, and when its bounded wait budget elapses first it returns output ending in state: running.
  • A user asking to resume maps to --resume <session-id> or --resume-last; these and --fresh are alternatives. Only a terminal job in the same workspace and mode is resumable. The shared session database lets a later job use ACP session/load on its session id; a resumed session keeps its model unless a new model is named. --fresh ignores continuity. A terminal job's config directory is removed, and a periodic sweep removes orphan run directories older than one hour.
  • history exposes a safe metadata projection with resumable session ids. It defaults to the current workspace, --all includes every recorded workspace, and --limit caps the number of jobs shown.
  • --cwd selects the workspace for task, review, status, history, result, and cancel. Status, result, and cancel search all recorded workspaces by job id when --cwd is omitted. A bad working directory, or an implicit task or review working directory below its Git repository root, fails before a job record is created. Worktree isolation means creating a real Git worktree before launch and supplying that path as the actual --cwd.
  • Review collects the working tree diff or a branch range, interpolates it into ${CLAUDE_PLUGIN_ROOT}/prompts/review.md, and runs a review mode job. The reply must contain one JSON object with verdict (approve or request_changes), summary, and findings (each with severity, file, line, title, and body). The companion extracts the first JSON object from the result text and validates it, and a missing or invalid object fails the review as error instead of falling back to prose.
  • Typed failure kinds are missing_cli, setup, auth, quota, rate_limited, network, permission, policy, refused, protocol, timeout, process, cancelled, died, input, resource, and error. Quota and rate limit failures carry billingPool; authentication, missing CLI, setup, protocol, permission, and policy failures are engine wide.
  • Outcomes end with the shared footer block: devin-session: <session-id> when a resumable session exists, then job:, sandbox:, delivery:, semantic:, any adapter warning: lines, state:, and failure: for error and cancelled outcomes.
  • Job records live at <data>/state/<workspace>/jobs/<id>.json, where <data> is DEVIN_COMPANION_DATA or ~/.claude/plugins/data/devin-claude-code-fusion. They carry engine: "devin" plus devinVersion, devinBuildPath, sessionId, requestId, requestedModel, resolvedModel, observedModel, requestedEffort, effortApplied, billingPool, mode, role, usage, stopCause, configDir, and warnings.
  • scripts/session-end-hook.mjs runs at Claude Code SessionEnd, performs verified cleanup of this session's running jobs, and removes unused raw transports.
  • Return the helper output exactly as received, whether the Bash tool reports it from stdout or stderr.
  • If the Bash call fails or Devin cannot be invoked, surface the failure instead of hiding it; the devin-rescue agent returns exactly one devin unavailable: <reason> line for the orchestrator's circuit breaker.

Read the full file on GitHub · 54 lines

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. today First seen · 54 lines · 19 tokens per session scan B 4b0545409e01

Subscribe to this mod's changes

devin-cli-runtime is a skill published in the GitHub repository okisdev/claude-code-fusion (3 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,580 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.

Related

Other skills, from other repositories

review-team

A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.

s977043/river-review · 147 tokens

eval-code-quality

Specialized code quality evaluator for the Evaluate-Loop. Use this for evaluating code implementation tracks where the deliverable is functional code — features, API routes, state management, utilities. Checks build integrity, type safety, code patterns, error handling, dead code, imports, test coverage, and naming…

Ibrahim-3d/orchestrator-supaconductor · 109 tokens

receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.

Ibrahim-3d/orchestrator-supaconductor · 38 tokens

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

Ibrahim-3d/orchestrator-supaconductor · 22 tokens

swarm-pi-review

Review a Git working tree or branch with read-only Pi workers. Use standard for bugs, security, regressions, and missing tests; use lean for diff-bound simplification, deletion, reuse, YAGNI, or native replacements. Route one question to ask and broader risk analysis to orchestrate.

JiaWeiXie/swarm-pi-code-plugin · 66 tokens

security-review

Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.

biggora/dev-team · 61 tokens