/do — Unified Intent Router

Orientation

Use /do when the user wants something done but doesn't know (or care) which tool handles it. Don't use when: you know the destination — invoke /marshal, /archon, /fleet, or any skill directly.

Commands

Protocol

Classification runs top-to-bottom. Exact commands resolve first. Natural-language requests use keyword matches only as candidate evidence for semantic classification.

Step 0: Skill Registry Check (Cost: ~0 on hit | ~50 tokens on miss)

Compare installed skill directories with core/skills/routing-table.json. If they match, continue without reading skill bodies. For each unknown skill, read only its frontmatter and use name, description, and trigger_keywords as session-local Tier 2 match targets, then report: "Discovered {N} new skill(s): {names}. Run /do setup to regenerate routing." Do not write registration fields into harness.json; schema-v2 config is exact and generated routing is a projection, not config authority.

Tier 0: Exact Command Match (Cost: ~0 tokens | Latency: <1ms)

Normalize case, apostrophes, and whitespace, then compare the entire input. Never match a Tier 0 command because its word appears inside a larger request.

/do preview <request> strips the preview wrapper and reuses the shared exact command and built-in candidate preflight. It does not inspect Tier 1 active state, discover project-local custom skills, or run the Tier 3 LLM classifier. Therefore every natural-language preview is non-final, has no command, and stops at semantic-classification-required. /do --route /skill -- <request> passes the requested route through scripts/route-preview.js --route; an unknown route is rejected, and a valid override still goes through activation, worktree, and approval boundaries.

If the whole input matches an exact command, execute it and stop. The test, build, and typecheck commands are final only when the target project's package.json declares the corresponding non-empty script. Otherwise they remain non-executable. Do not execute a command merely because its word appears inside a larger request; continue to active-state and semantic routing.

Tier 1: Active State Short-Circuit (Cost: ~0 tokens | Latency: <100ms)

Check for active campaigns or fleet sessions that match the input scope:

0. For input exactly equivalent to continue, first run:

   node scripts/continue-action.js --run

   • If it executes a local command such as node scripts/package-delivery.js <slug>, report the output and stop.
   • If it returns /archon continue, invoke /archon continue.
   • If it returns /fleet continue, invoke /fleet continue.
   • If it returns no command, output "No active campaign or fleet session found. Nothing to continue."
1. Read .planning/campaigns/ for files with Status: active or status: active in frontmatter
2. Read .planning/fleet/ for session files with status: active or needs-continue
3. Review-package campaigns: if the campaign status is needs-review-package or its review-package Exit Evidence row is pending while prior phases are complete, route to node scripts/package-delivery.js <slug> before Archon.
4. Improve campaigns (type: improve): if the active campaign has type: improve in frontmatter, route to /improve {target} --continue where {target} is the campaign's target field. Do NOT route improve campaigns to archon -- improve is its own orchestrator.
5. If input scope matches a non-improve active campaign → /archon continue
6. If fleet session needs continuation → /fleet continue
7. If input mentions a campaign by name → resume it (check type field for routing)
8. If input is "continue" but NO active campaign or fleet session found:
   • Output: "No active campaign or fleet session found. Nothing to continue."
   • If .planning/daemon.json exists with status: "running": the daemon spawned this session but there's no work to do. Update daemon.json: status: "stopped", stopReason: "no-active-work", stoppedAt: "{ISO timestamp}". Delete both triggers if IDs are present. Output: "[daemon] Stopped -- no active campaign found. The work is done."
   • Exit. Do NOT fall through to Tier 2 or 3.

If matched → resume the active work. Done.

Tier 2: Skill Candidate Discovery (Cost: ~0 tokens | Latency: <10ms)

Match input against installed skill keywords from Citadel's built-in skills and any project-level custom skills in .claude/skills/. These matches are candidate evidence, never the final routing decision by themselves.

Built-in skill triggers (generated from each skill's trigger_keywords frontmatter; edit the frontmatter, then run node scripts/generate-routing.js to refresh this table):

Script routes (hand-maintained; these dispatch to local scripts, not skills):

Carry every matching route and the exact matched phrases to Tier 3. A single candidate narrows the semantic decision but does not turn substring evidence into execution authority. Multiple candidates are disambiguated semantically, not by generated-table order.

Tier 3: LLM Complexity Classifier (Cost: ~500 tokens | Latency: ~1-2s)

For every non-exact request, classify intent across 6 dimensions. Use Tier 2 candidates as evidence when present; when none match, classify from the request:

SCOPE: single-file | single-domain | cross-domain | platform-wide
COMPLEXITY: 1 (trivial) | 2 (simple) | 3 (moderate) | 4 (complex) | 5 (campaign)
INTENT: fix | build | create | add | audit | redesign | research | improve | wire | prune
REQUIRES_PERSISTENCE: true | false (multi-session?)
REQUIRES_PARALLEL: true | false (independent sub-tasks?)
REQUIRES_TASTE: true | false (quality judgment beyond tests?)

Routing rules (first match wins):

Ambiguity gate: When multiple Tier 2 candidates survive or classifier confidence is below 0.7, and the AskUserQuestion tool is available: present the top 2-3 candidate routes as options, each with a label and a one-line tradeoff, and route to the user's pick. When unavailable, apply the rules above unchanged (tie-break, then /marshal default).

Important: A repeated pattern complaint ("I keep doing X manually", "the agent always makes this mistake") should route to /create-skill. A repeated pattern is a skill waiting to be extracted.

Step 3.5: Proportionality Check

After classification and before execution, verify the response is proportional to the input:

Downgrade triggers (apply in order):

Upgrade triggers:

Fleet auto-decomposition — 1/2/3 confirmation prompt:

When 2+ independent tasks detected (non-overlapping scopes, complexity >= 3, not already routed to full Fleet), read consent.fleetSpawn from harness.json:

• auto-allow → route directly to /fleet --quick
• always-ask or null → show prompt: "These look independent — run in parallel? [1=yes 2=always 3=no]"
  • 1: route to --quick, preference unchanged
  • 2: route to --quick, write writeConsent('fleetSpawn', 'auto-allow')
  • 3: run sequentially; if "don't ask again", write always-ask

readConsent/writeConsent are in hooks_src/harness-health-util.js. Trust level: Read from harness.json trust object. Levels: novice (0-4 sessions), familiar (5-19), trusted (20+ with 2+ campaigns). trust.override takes precedence.

Step 4: After Classification

1. Enforce product activation before invocation. Run: node {citadelRoot}/scripts/citadel-config.js check route {bare-skill-name} --runtime {claude-code|codex|opencode} --json. enabled and explicitly named degraded routes may continue. For disabled, unavailable, or blocked, show the returned reason and activation plan; do not invoke the target. Enabling a bundle is a separate plan-first config mutation and never happens silently. An explicit --route override changes only route selection. It never skips this activation preflight or any worktree, approval, or verification boundary.

2. Log routing decision (fire-and-forget): node .citadel/scripts/telemetry-log.cjs --event agent-complete --agent do-router --session routing --status success --meta '{"tier":N,"target":"[skill]","input_chars":M}'

   Use .citadel/scripts/telemetry-log.cjs (the project-local copy). If it doesn't exist, skip logging silently — never block routing on telemetry failure.

3. Announce the routing decision: "Routing to [target] because [one-sentence reason]"
4. Invoke the target skill or orchestrator
5. If the target fails or the user says "wrong tool", try the next tier up. If the target is already Tier 3 (marshal fails or user explicitly escalates from a failed marshal attempt): re-route to /archon with the original input as context, then repeat activation preflight for that route.

/do --list

Output a grouped skill list drawn from the system reminder's available skills. Group by category (Orchestration, App Creation, Code Quality, Research & Debugging, GitHub & CI, Infrastructure, Monitoring, Utilities, Observability). For each skill, show /name — one-line description plus its product bundle. Include a footer: "Direct invocation bypasses routing, but not product-bundle activation or safety gates."

Fringe Cases

• .planning/ does not exist: The router works without .planning/. Tiers 0, 2, and 3 are fully independent of it. Tier 1 (active-state short-circuit) reads .planning/campaigns/ and .planning/fleet/ — if those directories are absent, skip Tier 1 gracefully and fall through to Tier 2. Never crash on a missing .planning/ directory.
• harness.json missing: Use the bootstrap Standard + Core + Persistence activation preview. Core/Persistence routes may proceed; other bundles return an explicit activation plan. Do not write config during routing.
• Multiple skills match at Tier 2: Carry candidates to Tier 3 per Tier 2 disambiguation rule above.
• User input is empty or whitespace: Respond with the --list output and a prompt to provide a direction.
• Routed skill not found: Report "Skill not found" and fall back to Marshal as the safe default.

Contextual Gates

Disclosure: "Routing to [skill]. See that skill's contextual gates for reversibility." Reversibility: depends on routed skill — check the routed skill's reversibility Trust gates:

• Any: routing and dispatch; inherits trust gates from the routed skill.

Quality Gates

• Tier 0-2 must resolve in under 1 second
• Tier 3 classification must be transparent (announce reasoning)
• Never route a trivial task (complexity 1) to Archon or Fleet
• Never route a multi-session task to a bare skill
• If routing fails, default to Marshal (safe middle ground)
• A routed target must pass central activation preflight; fallback targets do not bypass this gate

Exit Protocol

After routing and execution complete:

• If the routed skill/orchestrator produces a HANDOFF, relay it to the user
• If the task was trivial (Tier 0), just show the result
• Do not add overhead to simple tasks
• Telemetry is fire-and-forget — never surface telemetry errors to the user