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.
/plugin marketplace add okisdev/claude-code-fusion/plugin install devinWrote 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/okisdev/claude-code-fusion/devin-cli-runtime)<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.
<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>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 | $0.00019 | $0.02580 |
| Opus 5.5 | $0.00008 | $0.01032 |
| Sonnet 5.5 | $0.00004 | $0.00516 |
| Haiku 4.5 | $0.00002 | $0.00258 |
Grade B, and why
devin-cli-runtime scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- Project scoped `AGENTS.md`, `AGENTS.local.md`, `AGENT.md`, `.windsurfrules`, and project skills under `.devin/skills`, `.cognition/skills`, and `.agents/skills` still load. Project `.devin/config.json`, `.devin/config. How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devin runtime
Primary helper:
node "${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-createandtransport-discard --raw-args-token <token>task-workerandreview-workerare 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-tokeninvocation. 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; usetransport-discardwhen 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
devinonPATH, withDEVIN_BINoverriding the path. Preflight runsdevin --versionand every job recordsdevinVersionanddevinBuildPath. - The tested interval is
[3000.11, 3000.12)by major and minor version. An older or unparseable build fails preflight assetup; a newer build runs and/devin:setupreports it as newer than the tested interval. The generated configuration disables background auto update. - Every run executes
devin acpwith the workspace as its working directory. The companion sends JSON-RPCinitialize,session/neworsession/load, the supportedsession/set_config_optionrequests, thensession/prompt. The brief appears only in that prompt message. The companion never passes--cloud,--agent-type,--model, or--refusal-fallback. Permission requests receivecancelled. - Consult is the default mode,
--writeselects write mode, andreviewis always read only. Consult and review set ACP modeaskand allowread,grep,glob,find_file_by_name,notebook_read, andtodo_write. Write setsautonomousand additionally allowsedit,write,notebook_edit,exec,get_output,kill_shell, andwrite_to_process. Atool_calloutside the mode list terminates the process group and fails aspolicy. - Consult and review deny edit and exec in the generated configuration. Write sets
DEVIN_SANDBOX=trueand allowsWrite(<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 andFetch(*)are denied in every mode; other home reads may remain possible. - Every job uses shared private
HOME,XDG_DATA_HOME,XDG_STATE_HOME, andXDG_CACHE_HOMEunder<data>/home, and privateXDG_CONFIG_HOMEat<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. Generateddevin/config.jsondisables auto update, attribution, subagents, notifications, and personal imports, anddevin/mcp_config.jsonhas emptymcpServers. The child environment never inheritsDEVIN_*variables. - Project scoped
AGENTS.md,AGENTS.local.md,AGENT.md,.windsurfrules, and project skills under.devin/skills,.cognition/skills, and.agents/skillsstill load. Project.devin/config.json,.devin/config.local.json,.devin/mcp_config.json, and.devin/mcp_config.local.jsonmay 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
--modeland--effortfrom the routing table. A direct user call without--modeluses the account default.modelsreadsdevin models list --format json, caches the family catalog for one hour, and--refreshreads it again. - Models are family slugs such as
kimi-k3,glm-5.2,muse-wonder, andswe-2, their aliases, or variant uids. The companion matches the requested family to a usable session model option and records that option asresolvedModel. A missing catalog family fails before job creation asinput; a family unavailable to the account fails assetup. Effort is the selected model'sthought_level:defaultleaves its default, a supported level is set explicitly, and an unsupported level fails asinput.speedis set tostandardwhen offered.adaptiveandfusion-*pairings are refused asinput. - The
_cognition.ai/agent_stoppedor_cognition.ai/turn_statsevent reports the serving model asobservedModel; a difference from the selected display name rendersmodel_mismatchwithout changing the transport outcome.billingPoolisfirst-partyforswe-*models andapifor 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 withstopReason: "end_turn"and an agent stopped cause ofcompletefor success. It recordsusageexactly as reported, without filling absent cache tokens or reporting cost. Malformed lines or an exit before the prompt result fail asprotocol. - 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 recordinglate_close. The run timeout isDEVIN_COMPANION_TIMEOUT_MS(default 540000).DEVIN_COMPANION_WAIT_TIMEOUT_MS,DEVIN_COMPANION_WAIT_POLL_MS, andDEVIN_COMPANION_PIDLESS_RUNNING_GRACE_MSuse the companion defaults. - Ordinary delegations use one foreground helper call with timeout
600000. Only an explicit incoming user--backgrounddetaches a task or review into an internal worker and creates a manual receipt; the helper prints the job id plus/devin:statusand/devin:resulthints. Never add--backgroundbecause a task appears large or slow, and never use Bash background mode.result --waitblocks while a job is running, and when its bounded wait budget elapses first it returns output ending instate: running. - A user asking to resume maps to
--resume <session-id>or--resume-last; these and--freshare alternatives. Only a terminal job in the same workspace and mode is resumable. The shared session database lets a later job use ACPsession/loadon its session id; a resumed session keeps its model unless a new model is named.--freshignores continuity. A terminal job's config directory is removed, and a periodic sweep removes orphan run directories older than one hour. historyexposes a safe metadata projection with resumable session ids. It defaults to the current workspace,--allincludes every recorded workspace, and--limitcaps the number of jobs shown.--cwdselects the workspace for task, review, status, history, result, and cancel. Status, result, and cancel search all recorded workspaces by job id when--cwdis 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 withverdict(approveorrequest_changes),summary, andfindings(each withseverity,file,line,title, andbody). The companion extracts the first JSON object from the result text and validates it, and a missing or invalid object fails the review aserrorinstead 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, anderror. Quota and rate limit failures carrybillingPool; 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, thenjob:,sandbox:,delivery:,semantic:, any adapterwarning:lines,state:, andfailure:for error and cancelled outcomes. - Job records live at
<data>/state/<workspace>/jobs/<id>.json, where<data>isDEVIN_COMPANION_DATAor~/.claude/plugins/data/devin-claude-code-fusion. They carryengine: "devin"plusdevinVersion,devinBuildPath,sessionId,requestId,requestedModel,resolvedModel,observedModel,requestedEffort,effortApplied,billingPool,mode,role,usage,stopCause,configDir, andwarnings. scripts/session-end-hook.mjsruns 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.
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.
- today First seen · 54 lines · 19 tokens per session scan B 4b0545409e01
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.
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.
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…
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.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
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.
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.