Devin CLI Orchestrator - Cross-AI Task Delegation
CRITICAL — SELF-INVOCATION PROHIBITED
This skill dispatches to the Cognition CLI binary (
devin). If the agent currently reading this skill is itself running inside Devin (detection signals listed inROUTER.md§3), the skill MUST refuse to load and return the documented error message instead of generating anydevininvocation.A running CLI skill never dispatches itself. The cli-X skills are for cross-AI delegation only — never self-invocation.
Orchestrate Cognition's Devin CLI for tasks that benefit from a second AI perspective, multi-model selection (DeepSeek, GLM-5.2, GPT-5.6 Luna Max, Grok (4.5 and 4.6), SWE-2), subagent delegation with run_subagent, cloud handoff via /handoff, or parallel code generation.
Core Principle: Use Devin for what it does best. Delegate, validate, integrate. The calling AI stays the conductor.
1. WHEN TO USE
Activation Triggers
- Cross-AI Validation — code review second perspective, security audit alternative analysis, bug detection, independent implementation attempts.
- Cloud Handoff — long-running tasks, complex refactors, CI-like validation, browser-dependent workflows offloaded to a cloud Devin session via
/handoff. - Subagent Delegation — specialized profile matches (
subagent_explore,subagent_general, custom.devin/agents/[name]/AGENT.mdprofiles), parallel task processing through Devin's native subagent system. - Multi-Model Dispatch — tasks that specifically want a model available through Devin's multi-model surface (DeepSeek, GLM-5.2, GPT-5.6 Luna Max, Grok (4.5 and 4.6), SWE-2), selected per-dispatch with
--model. - Parallel Code Generation — offloading generation, simultaneous code generations, background docs/test generation through subagents.
- Specialized Generation — explicit Devin requests, test suite generation, code translation, batch documentation, visual input via clipboard paste or
@file mentions.
When NOT to Use
- You ARE Devin already. If your runtime is Devin (detection signal:
$DEVIN_PROJECT_DIRenv var set,devinin process ancestry, or credentials present at~/.local/share/devin/credentials.tomlwhile a session is active), this skill refuses to load. Self-invocation creates a circular dispatch loop and burns tokens for no value. - Simple, quick tasks where CLI overhead is not worth it, or tasks needing an immediate response (auth/network round-trips may delay).
- Context already loaded and understood by the current agent.
- Interactive refinement requiring the full-screen REPL (use
devindirectly instead). - Tasks where Devin CLI is not installed.
2. SMART ROUTING
The hub's cli-devin mode signal routes a Devin CLI dispatch here when a request names devin, Cognition, an autonomous SWE dispatch, a cloud handoff or a subagent.
references/cli-reference.md and assets/prompt-quality-card.md load on every invocation; the hub ROUTER.md names the mode's first leaves.
Read ROUTER.md before selecting skill-local resources; open only the matched files.
3. HOW IT WORKS
Prerequisites
Install via devin setup (interactive wizard) or curl -fsSL https://devin.ai/install | bash.
cli-devin authenticates through Devin account OAuth. Run devin auth login and complete the browser flow (or --force-manual-token-flow for SSH/remote sessions).
Full install, auth, flag, permission-mode, session, and troubleshooting tables live in the ALWAYS-loaded cli-reference.md. This section keeps only the routing decisions and dispatch-critical gotchas.
Execution Ownership
This packet owns user-facing routing, the command -v devin availability probe, prompt construction, and the self-invocation guard.
Research and review lineages delegate process construction and execution to the deep-loop runtime at ../../system-deep-loop/runtime/scripts/fanout-run.cjs, using executor kind cli-devin. That runner accepts only the research and review loop types, so a single build or doc dispatch uses the child dispatch envelope in providers-and-models.md §5.
The runtime is the single Devin execution adapter. Do not add a packet-local wrapper, command builder, or spawn path. Direct devin -p snippets below are operator reference and manual-testing examples; research and review lineages use the shared runtime, and a one-shot dispatch uses the child envelope.
Provider Auth Pre-Flight (Devin Account OAuth)
MANDATORY before any first dispatch in a session. cli-devin authenticates through Devin account OAuth only. If devin auth login has not been completed on this machine, a dispatch fails with an authentication error mid-round-trip. Run this check once per session, cache the result, and re-run it only if a dispatch fails with an auth error.
# One-shot pre-flight: capture Devin auth status for routing
DEVIN_AUTH=$(devin auth status 2>&1)
echo "$DEVIN_AUTH" | grep -qi "logged in" && DEVIN_AUTH_OK=1 || DEVIN_AUTH_OK=0
Decision tree (apply in order — first match wins):
| State | DEVIN_AUTH_OK | Action |
|---|---|---|
| OAuth ready | 1 | Proceed with devin -p --model <model> --permission-mode <mode> -- "<prompt>" |
| Not logged in | 0 | ASK user to run devin auth login — surface the command, do NOT dispatch. Never substitute a different auth method or skip the check. |
User prompt template — not logged in:
Devin is not authenticated on this machine. cli-devin uses Devin account OAuth only.
Run `devin auth login` (browser flow; or `devin auth login --force-manual-token-flow` for SSH/remote),
then confirm when login finishes — the skill will retry the original dispatch.
Error-recovery contract. If a dispatch returns an auth error after pre-flight passed (OAuth expired or revoked), invalidate the cache, rerun devin auth login, and re-check before retrying. Never substitute a model the user didn't approve.
Default Invocation (Skill Default)
Default model + permission mode: swe-2-max · dangerous permission mode. The CLI's own swe alias is not pinned, so every dispatch names swe-2-max.
devin -p \
--model swe \
--permission-mode dangerous \
-- \
"<prompt>"
Why
dangerousis the default for implementation work. Underaccept-editsDevin may edit files but every other tool call is refused withwarning: rejected a tool call that requires confirmation. In a non-interactive-psession there is nobody to confirm, so the dispatch cannot read a module to check an export, cannot grep, and cannot run the tests it was asked to run. The observed failure is not an error — it is a dispatch that spends its whole budget exploring, writes nothing, and exits 0. A caller who does not diff the worktree afterwards will read that as success.The marginal risk is smaller than the name suggests:
accept-editsalready grants arbitrary file modification, which is the destructive capability.dangerousadds the ability to run commands, which is what lets the executor verify its own work instead of handing back unverified edits. Useautofor read-only review, analysis, and research, where no elevation is needed.
autois read-only, not tool-free. It refuses any tool call that wants confirmation, and a shell command counts even when the command only reads. Observed on 2026-09-15: a crawl dispatched underautodecided on its own to run agitcommand to check state, was refused withwarning: rejected a tool call that requires confirmation, and exited 0 having reported almost nothing. A research dispatch that might shell out therefore needsdangerouswith a read-only instruction in the prompt, and the caller diffs the worktree afterwards to confirm it wrote nothing. Reserveautofor a dispatch whose whole job is reading files.
User override (honor explicit user phrasing verbatim):
| User says | Resolve to |
|---|---|
| (nothing specified) | --model swe-2-max --permission-mode dangerous |
| "Use glm" / "Use glm high" | --model glm-5-2 --permission-mode dangerous |
| "Use glm no-thinking" | --model glm-5-2-none --permission-mode dangerous |
| "Use glm max" | --model glm-5-2-max --permission-mode dangerous |
| "Use deepseek" | --model deepseek-v4-flash-max --permission-mode dangerous |
| "Use swe max" | --model swe-2-max --permission-mode dangerous |
| "Use glm accept-edits" | --model glm-5-2 --permission-mode accept-edits |
| "Use autonomous sandbox" | --sandbox --permission-mode autonomous |
Fan-out fallback: a deep-loop lineage that pins no model runs SWE 2 Max. The family is named here on purpose, without a version or an effort tier, so this line does not go stale when the family ships a point release; the runner resolves the current id. A drift test keeps the two in the same family.
Honor the dimensions the user names. Otherwise the model stays swe and the permission mode stays dangerous.
Model Selection
Default swe-2-max. Switch per-dispatch with --model <name>; there is no headless reasoning-effort flag, so autonomy is set through --permission-mode.
Curated families, alphabetical:
- DeepSeek:
deepseek-v4-1-flash-high,deepseek-v4-1-flash-max,deepseek-v4-flash-max. - Gemini:
gemini-3-8-flash-high. The uid spells the family with dashes while the Cursor scope spells the same model with dots. - GLM-5.2:
glm-5-2= GLM-5.2 High, free tier;glm-5-2-1m= High 1M;glm-5-2-max= Max;glm-5-2-max-1m= Max 1M;glm-5-2-none= No Thinking;glm-5-2-none-1m= No Thinking 1M. - GLM-5.3:
glm-5-3-flash-high,glm-5-3-flash-max. - GPT-5.6 Luna Max:
gpt-5-6-luna-max,gpt-5-6-luna-max-priority. - GPT-6 Luna Max:
gpt-6-luna-max,gpt-6-luna-max-priority. A separate family from GPT-5.6. - SWE-2:
swe-2-max,swe-2-high,swe-2-medium; free, 262K context. - SWE-1.7:
swe-1-7,swe-1-7-lightning,swe-1-7-medium.
Full roster and the permission-mode effort lever in references/providers-and-models.md.
Selection Strategy: default swe-2-max for everyday and cost-sensitive work, with swe-2-medium for quick edits; switch to gpt-5-6-luna-max for reasoning-heavy work (architecture, security, deep planning); use glm-5-2 / glm-5-2-max for general generation. Per-task rationale table: cli-reference.md §5.
Devin Subagent Delegation
The calling AI is the conductor. Devin's run_subagent tool spawns independent workers that share tools and codebase context but operate in their own conversation chain.
Two built-in profiles (subagent_explore read-only, subagent_general full-access) plus custom .devin/agents/[name]/AGENT.md profiles shape HOW Devin processes the subtask.
Full roster and invocation patterns: agent-delegation.md.
| Task Type | Profile | Model |
|---|---|---|
| Read-only codebase exploration | subagent_explore |
Default subagent model (SWE-1.6) |
| General-purpose code changes | subagent_general |
Same as parent agent |
| Custom specialized worker | .devin/agents/[name]/AGENT.md |
Pinned in AGENT.md or default |
Subagents run foreground (parent pauses) or background (parallel, auto-deny unapproved tools). The run_subagent tool takes a profile, not a model — to pin a model on a write-capable subagent, use a custom AGENT.md with a model: field.
Devin Skills, Rules, and Native Agent Profiles
Devin discovers the skills and rules already in the repository, and this packet adds no adapter for either.
A session loads the checkout's root AGENTS.md, cut at Devin's fixed 16,384-byte limit per rule file, because .devin/config.json turns the Claude import off.
The live devin skills list and devin rules list output is recorded in agent-delegation.md §10.
Agent Roster Parity
All 11 repo agents are dispatchable through run_subagent: ai-council, code, context, debug, deep-research, deep-review, design, markdown, orchestrate, prompt-improver, review. A live roster probe lists them alongside Devin's own subagent_explore and subagent_general.
Each .devin/agents/<name>/AGENT.md is a symlink to the canonical .claude/agents/<name>.md, matching the discovery-mirror precedent already used for .claude/hooks/ and .codex/hooks/. One source of truth, so a mirror can never drift from the agent it mirrors.
This works because Devin's failure with Claude-format agents is a discovery-path limitation, not a format-parsing one: the same file Devin ignores at .claude/agents/<name>.md registers correctly once reachable at Devin's own .devin/agents/<name>/AGENT.md path -- Claude's tools: frontmatter field is accepted as-is, so no per-agent translation to allowed-tools: is needed.
Invoke by naming the profile explicitly:
command -v devin
devin --permission-mode bypass -p \
"Use the review subagent to review the current diff for correctness, security, and repository-convention consistency. Cite file paths and line numbers." \
2>&1
The experimental native profile format (docs.devin.ai/cli/subagents) and its YAML fields are in agent-delegation.md §5.
Installed-Version Findings
Devin 3000.2.17 does not import .claude/agents/*.md as its docs claim, so the .devin/agents/<name>/AGENT.md symlinks above exist, and it has no command-file system. The probes behind both findings are in agent-delegation.md §10.
Cloud Handoff
Devin's unique /handoff command transfers the current session to a cloud Devin session with its own VM, shell, browser, and full repo access. Use for long-running tasks, complex refactors, CI-like validation, browser-dependent workflows, and parallel execution. Full mechanics and state transfer: cloud-handoff.md.
Dispatch-Critical Gotchas
The full flag glossary, permission modes, unique capabilities (/handoff, run_subagent, devin mcp, session resume/continue, --sandbox), essential command examples, and troubleshooting table are in the ALWAYS-loaded cli-reference.md. Four gotchas that silently break a dispatch and must be honored at routing time:
devin -pis non-interactive and exits after one turn — it prints the response to stdout and exits. For multi-turn work, usedevin -c(continue) ordevin -r <session-id>(resume). Do not expect a REPL from-p.--permission-modedefaults toauto(read-only auto-approve). File-modification tasks silently prompt or no-op without elevated mode.- Pass
--permission-mode dangerouswhenever the task requires edits. accept-editsis only half a grant. It permits writes but refuses the reads and commands an implementer needs, so a dispatch under it can burn its whole budget and exit 0 having written nothing.- The
--sandboxflag selectsautonomousmode, the only mode available in sandbox sessions.
- Pass
devin -prejects MCP tool calls underauto/accept-edits(andsmartmay be unavailable). When a least-privilege MCP allowlist is preferable to blanket elevation, grant it in a machine-local config:
// .devin/config.local.json
{ "permissions": { "allow": ["mcp__<server>__*"] } }
Then auto/accept-edits auto-approve exactly those MCP tools; reserve dangerous for throwaway isolated runners.
- Always pass
--modelexplicitly in scripts — omitting it relies on the caller's~/.config/devin/config.jsondefault, which may be a different model. Explicit means reproducible regardless of who runs it. - Model ids carry no
-highsuffix, but the interactive picker shows one — the TUI labelsglm-5-2as "GLM-5.2 High", so an operator asking for "GLM 5.2 high" means the idglm-5-2. Noglm-5-2-highexists.devin models listis the authority for every id and its display name; this document's roster is a convenience copy. - A free-tier model still dispatches when the Pro quota reads 0% —
glm-5-2is billed as Free, and a dispatch succeeded withPro · 0% remainingshowing in the TUI. Quota exhaustion gates the paid families, so do not abandon a dispatch on the quota banner alone; probe with a trivial read-only call first. devin --helpis NOT the authoritative--permission-modeenum. It prints 4 values; the binary accepts 8.- Canonical set with aliases:
normal(auto),accept-edits,smart,dangerous(yolo,bypass),autonomous(requires--sandbox). - Do not "correct" a mode value in this skill because help omits it. That conclusion is wrong and has been reached before.
- Probe instead:
devin --permission-mode <value> --prompt-file /nonexistent(exit 2 = rejected, exit 1 = accepted). - The enum also moves between releases, so re-probe after an upgrade rather than trusting either help or this line.
- Canonical set with aliases:
- Use
--before every print-mode prompt —devin -p -- "list all TODO comments"prevents the prompt from being parsed as CLI flags. The prompt must follow the separator, or load it with--prompt-file.
4. RULES
✅ ALWAYS
Verify Devin CLI is installed before first invocation (
command -v devin).Delegate research and review lineages to
../../system-deep-loop/runtime/scripts/fanout-run.cjswith executor kindcli-devin. It rejects every other loop type, so a single build or doc dispatch uses the child dispatch envelope in providers-and-models.md §5. Never build a second adapter in this packet.Use
--permission-mode autofor review/analysis/research, and--permission-mode dangerousfor code generation and file modification.devin -pitself defaults toauto, so omitting the flag causes a silent no-op on edit tasks. Preferdangerousoveraccept-editsfor any task that must read files or run its own verification;accept-editsrefuses those calls and the dispatch fails silently.Validate Devin-generated code (XSS, injection, eval, syntax checks via
node --check,tsc --noEmit, etc.) before applying.Capture stderr (
2>&1) so rate-limit messages and errors surface.Redirect devin stdin from
/dev/nullon EVERY non-interactive dispatch, not only inside awhile readloop, the condition this rule used to name and the reason it was skipped. Pattern:devin -p -- "$PROMPT" > "$LOG" 2>&1 </dev/null &. Without</dev/null, the backgrounded devin process inherits the loop's stdin and silently consumes the remaining lines. Seereferences/integration-patterns.md#background-execution→ "Silent Stdin Consumption".Specify model + permission mode explicitly — never rely on caller environment. Default:
--model swe --permission-mode dangerous. Honor user overrides verbatim. Usegpt-5-6-luna-maxfor reasoning-heavy tasks (architecture, security, deep planning).Route to the appropriate subagent profile when the task matches a specialization (see Section 3 routing table); use
subagent_explorefor read-only research,subagent_generalfor code changes.Pass the spec folder to the delegated agent in the prompt: if the calling AI has an active Gate-3 spec folder, include
Spec folder: <path> (pre-approved, skip Gate 3). If none, ASK the user before delegating — the delegated agent cannot answer Gate 3 in non-interactive-pmode.Prompt construction & model-craft (cli- family precedence).* Compose every dispatch prompt via the 2-tier rule canonical in
../../sk-prompt/assets/cli-prompt-quality-card.md:- Fast path (default). Build from the local
assets/prompt-quality-card.md, which delegates the framework table + CLEAR check to the canonical card. - Deep path (escalation). Dispatch
@prompt-improvervia the Task tool (never load fullsk-promptinline) when any canonical Tier 2 trigger applies — the trigger list lives in../../sk-prompt/assets/cli-prompt-quality-card.mdunder "Tier 2 — Deep path"; do not re-enumerate it here.
- Fast path (default). Build from the local
Never inject user-level voice/personalization content into AI-orchestrated Devin delegations. Devin CLI reads user-level rules from
~/.config/devin/and project.devin/config. When an AI delegates viadevin -p, the calling AI's own voice rules govern the response. Do NOT read user config and paste into delegation prompts. Keep delegations focused on task/model/permission-mode/(spec-folder pre-approval). If the user asks how to make Devin sound more like another tool in their own sessions, point to~/.config/devin/config.json, not any repo asset.Code Standards Loading (surface-aware contract) — When dispatching for code review or code generation, instruct the dispatched session to:
- load
sk-code; - let
sk-codeemit a surface tag matching the detected stack from markers and target files; - load the selected surface resources and run its verification commands;
- add
code-reviewonly for formal findings-first review output. Fallback: if the surface cannot be determined confidently, ask for the runtime surface and verification command set. NEVER hardcode obsolete sibling code skills in dispatch prompts.
- load
Design Standards Loading (measured-reference contract) — When dispatching for design or UI work, instruct the dispatched session to:
- load
sk-design-md-generator; - extract a measured Style Reference DESIGN.md from the live source before building UI, with named color tokens, type scale, components, Quick-Start CSS/Tailwind;
- build against those measured tokens and run the extraction's validate step to confirm hex/section fidelity.
Fallback: if there is no live source to measure, ask for the reference URL or the exact tokens to build against. NEVER treat
mcp-figmaorsk-design-md-generatoras a taste, visual-direction, or critique authority. The extraction measures real CSS, it does not judge design.
- load
Pass the design reference manifest to the dispatched session. When dispatching design or UI work, inline a
DESIGN_DISPATCH_MANIFEST v1block in the prompt. The child cannot resolve skill paths, so the manifest travels in the payload, not by reference. It carriesstyleReferenceExtractedtrue, the livesourcethat was measured, the measured design tokens / type scale / components the child must build against,loadedFiles, andproofDemandBack. If the manifest cannot be assembled, because no Style Reference was extracted or there is no live source to measure, ASK before launching the child rather than starting a silent design dispatch. The child returns the demanded proof; the parent reconciles it on the return path.Single-dispatch discipline (operator-gated, session-scoped). Default: launch ONE cli-* dispatch at a time across the cli-* family (cli-devin, cli-codex, cli-claude-code, cli-opencode, cli-cursor). Wait for the dispatched agent's work to return, verify outputs exist, then SIGKILL only the dispatch THIS skill started.
- Capture the PID at launch (
devin -p -- ... & DEVIN_PID=$!) and kill that captured PID directly plus its own orphan children (kill -9 "$DEVIN_PID" 2>/dev/null; pkill -9 -P "$DEVIN_PID" 2>/dev/null), then apply the same PID-scopedgtimeoutcleanup. - Never use a blanket
pkill -9 -f "devin -p"pattern. It kills EVERY runningdevinprocess on the machine, including the operator's unrelated devin sessions. - Only launch the next dispatch (this skill OR a sibling) after the prior one is dead and RSS has dropped.
- Within a deep-flow session (deep-review / deep-research): the operator authorizes the whole multi-iteration session at start. Iterations chain back-to-back with kill-between as the safety mechanism, NOT a per-iteration confirmation prompt.
- Exception (cross-skill parallel): when the operator explicitly authorizes N parallel dispatches, run N concurrently, but still SIGKILL each by its own captured PID as its work returns.
- Capture the PID at launch (
Set
AI_SESSION_CHILD=1in the dispatched child's env AND state the exemption in the prompt. The variable makes the waiver true; it does not make it observable. The reader being waived is a model, and a model cannot see an environment variable, so a child given only the variable still stops to ask the documentation-scope question and writes nothing, at exit code zero. Copy the preamble fromshared/references/child-dispatch-preamble.mdto the top of every non-interactive prompt. The variable also matters for the per-session worktree wrapper (.skilled/bin/worktree-session.sh). A dispatcheddevin -pis an orchestrated sub-session, not a new top-level session, so it must SHARE the parent's worktree, not allocate its own. The wrapper checksAI_SESSION_CHILD(plus agit --git-common-dirstructural backstop) and exec's in place when set. Pattern:AI_SESSION_CHILD=1 devin -p -- ... </dev/null. Harmless when the wrapper is not in use. See.skilled/bin/README.md→ "Worktree session isolation".Agent-persona injection (attach identity, not just the task). Every dispatch composes
{resolved agent persona + task prompt}— never a bare task.- Resolve the persona from the ACTIVE runtime's agent directory per AGENTS.md §9 (
.skilled/agents/<name>.md,.claude/agents/<name>.md, etc. — never hardcode one runtime). - Map each subtask to the RIGHT agent (
code→code,review→review,design→design, research→deep-research, docs→markdown), not one default. - Devin has a native persona surface: dispatch via
run_subagentnaming the resolved profile (.devin/agents/<name>/AGENT.mdmirrors all 11 canonical agents; see "Agent Roster Parity"). Native resolution satisfies the rule. - On a bare top-level
devin -pthat names no subagent, INLINE the persona block into the payload using the same in-payload pattern as theDESIGN_DISPATCH_MANIFEST(Rule 14). The child cannot resolve agent paths by reference. - A persona-less dispatch runs the leaf as a generic assistant, silently dropping the agent's tool-scope, verification gates, and output contract.
Canonical contract:
../../sk-prompt/assets/cli-prompt-quality-card.md"Persona Injection"; native precedent:orchestrate.md"Agent Loading Protocol". Rare exceptions (native surface used, focused summary for a small-context model, pure-mechanical command) are declared at the dispatch site.
- Resolve the persona from the ACTIVE runtime's agent directory per AGENTS.md §9 (
⛔ NEVER
- Use
--permission-mode dangerousin a task the user has not approved it for (full shell beyond workspace = damage risk). One explicit approval covers every dispatch in that task, the default invocation included, and a new task needs a new approval.accept-edits(workspace edits auto-approve) does not require pre-approval. - Trust Devin output blindly for security-sensitive code, send sensitive data (API keys, passwords, credentials) in prompts, or hammer the API with rapid sequential calls.
- Use Devin for tasks where context is already loaded — direct action by the calling AI is faster.
- Assume Devin output is correct without verification — cross-reference codebase and project standards.
- Build or maintain a packet-local Devin execution adapter; the deep-loop runtime is the execution authority.
⚠️ ESCALATE IF
- Devin CLI is not installed and user has not acknowledged (provide
devin setupor install URL). - Rate limits are persistently exceeded (suggest checking the Devin account's plan and usage limits).
- Devin output conflicts with existing code patterns (present both perspectives; user decides).
- Task requires
--permission-mode dangerousand the user has not approved it for this task (describe the risks and ask once for the whole task).accept-editsdoes not require escalation. - Cloud handoff is requested for a task involving sensitive data or production systems (confirm the cloud session's isolation and data handling before handing off).
Memory Handback Protocol
When the calling AI needs to preserve session context from a Devin CLI delegation, run the canonical procedure: extract the MEMORY_HANDBACK section, build structured JSON, scrub secrets, then invoke generate-context.js via --stdin/--json/temp-file.
The continuity writer is the last step; nothing is handed to an index. Full procedure and caveats: system-spec-kit/references/cli/memory-handback.md. Devin-specific Memory Epilogue template: assets/prompt-templates.md §12.
printf '%s' "$JSON_PAYLOAD" | node .skilled/skills/system-spec-kit/runtime/cli/dist/continuity/generate-context.js --stdin [spec-folder]
5. REFERENCES
Core References
- cli-reference.md - Complete CLI subcommands, flags, permission modes, and config reference
- integration-patterns.md - Cross-AI orchestration patterns and workflows
- devin-tools.md - Built-in capabilities documentation (run_subagent, /handoff, MCP, session management, Fetch)
- agent-delegation.md - Subagent profile roster, routing table, and invocation patterns
- cloud-handoff.md - /handoff cloud-handoff mechanics, use cases, and state transfer
- providers-and-models.md - Curated model families, aliases and defaults
- manual-testing-playbook.md - 20-scenario Devin-native manual validation package
Templates and Assets
- prompt-templates.md - Copy-paste ready prompt templates for common tasks
- prompt-quality-card.md - Fast-path prompt framework + CLEAR check (ALWAYS loaded)
Shared (cli-* family)
- shared-smart-router.md - Helper-function bodies for the smart router.
- memory-handback.md - Canonical 7-step Memory Handback procedure.
External
- Devin CLI Documentation - Official CLI documentation
- Devin Web App - Cloud session management and tracking
Reference Loading Notes
- Load only references needed for current intent;
ROUTER.mdis the single routing authority. cli-reference.mdis ALWAYS loaded as baseline.
6. SUCCESS CRITERIA
Task Completion
- Devin CLI invoked with correct subcommand, flags, model, and permission mode.
- Output captured, validated, and integrated appropriately; no security vulnerabilities introduced.
- Rate limits handled gracefully (retry or fallback strategy).
- Appropriate subagent profile and permission mode matched to task type (auto/accept-edits for review, accept-edits/dangerous for generation).
- Cloud handoff used when the task benefits from a VM, browser, or long-running execution.
- Orchestrated execution delegated to the shared deep-loop runtime without a packet-local adapter.
Skill Quality
- All 8 sections present with the required H2 headings.
- Smart routing covers all intent signals with UNKNOWN_FALLBACK.
- Reference files provide deep-dive content without duplication.
7. INTEGRATION POINTS
Framework Integration
This skill operates within the behavioral framework defined in AGENTS.md.
Key integrations:
- Gate 2: Skill routing via
skill_advisor.py - Tool Routing: Per AGENTS.md Section 5 decision tree
- Continuity: Context preserved by
/speckit:save, which writes throughgenerate-context.js - Execution: Shared deep-loop runtime (
../../system-deep-loop/runtime/scripts/fanout-run.cjs)
Tool roles: Bash dispatches the CLI; Read/Glob/Grep validate output.
8. REFERENCES AND RELATED RESOURCES
The router discovers reference, asset, and script docs dynamically (Section 5 is the authored index). Start with the ALWAYS-loaded references/cli-reference.md and assets/prompt-quality-card.md, then load task-specific resources per Smart Routing.
Related skills: cli-codex for OpenAI-backed dispatch, cli-claude-code for extended reasoning, cli-opencode for full OpenCode runtime dispatch, cli-cursor for Composer/shared-editor-config dispatch, sk-code for code-quality contracts, mcp-code-mode for external MCP work, and system-spec-kit for packet handback.