Task Complexity Routing (SNC)

SkillProductivity

Scores how complex a coding task is and sets the right level of autonomy, review depth, and approval needed.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Task Complexity Routing (SNC) skill

About this capability

Scores a coding task on Spread, Novelty, and Centrality (SNC 0-6) and maps the tier to autonomy, verification depth, review mode, reviewers, model tier. Use when sizing a fix or feature before planning, choosing fast vs deep review, or deciding whether HARD STOP approval is required.

What this skill tells your AI

The instructions your AI receives, as published by hoangnguyen0403/agent-skills-standard in skills/common/common-task-complexity-routing/SKILL.md and read by ahel’s review.

Priority: P1 (HIGH)

Same ticket label, different engineering difficulty. Score the task, not the label, then route by tier.

Score

Dimension012
Spread (how far the change reaches)one file, one moduleseveral files, one modulecross-module or cross-service
Novelty (new vs existing behavior)small edit or removal of existing behaviormodify existing logicnew behavior or rewrite
Centrality (how core the touched code is)peripheral codeshared but non-corecore domain, hot path, auth, money, trust boundary

Sum the three, never average. Output line: SNC: S=[0-2] N=[0-2] C=[0-2] total=[n] tier=[low|medium|high].

Tiers

  • tier=low: total 0-2
  • tier=medium: total 3-4
  • tier=high: total 5-6

Routing

TierAutonomyVerificationReviewApprovalmodel_tier
tier=lowautonomousbasic: focused tests + lintfast code-reviewnone requiredfast
tier=mediumguidedTDD + self-reviewdeep code-reviewplan reviewed, no HARD STOPstandard
tier=highplan-firstTDD + independent reviewers (specialist-architecture-guard, specialist-security-reviewer when relevant)deep code-reviewHARD STOP before code, human approval before mergestrong

Rules

  • Score before planning; emit snc_tier and model_tier in every Handoff Payload.
  • Label the score as inference when derived from ticket text alone; re-score after specialist-codebase-scout reports impact radius.
  • Round up on doubt. Any auth, money, trust-boundary, or hot-path touch is C=2.
  • Re-score when scope grows mid-task; the tier may only rise, never fall, once work has started.
  • Never downgrade a tier to skip a gate. Ticket type (bug vs feature) never sets the tier.

Red Flags

Stop and re-score when hearing or thinking: "it's just a bug fix", "one-line change", "skip the plan, it's small", "we'll review it later", "mark it low so we can merge tonight". Each is a rationalization, not a score.

Anti-Patterns

  • No tier by ticket type: "bug" and "feature" say nothing about S, N, or C.
  • No averaging: three 1s and one 2/0/1 both route differently only when summed.
  • No silent tier: a plan or handoff without snc_tier is incomplete.
  • No high tier without named reviewers: tier=high must list which specialists review before merge.

References

Signals

GitHub stars
569
Forks
163
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
common-task-complexity-routing
Source
github.com/hoangnguyen0403/agent-skills-standard