Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/navapbc/digital-service-orchestraWrote 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/agents/navapbc/digital-service-orchestra/complexity-evaluator)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/complexity-evaluator"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/complexity-evaluator/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/agents/navapbc/digital-service-orchestra/complexity-evaluator"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/complexity-evaluator.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 | $0.00042 | $0.03778 |
| Opus 5 | $0.00021 | $0.01889 |
| Sonnet 5 | $0.00008 | $0.00756 |
| Haiku 4.5 | $0.00004 | $0.00378 |
Grade A, and why
complexity-evaluator scanned grade A with 0 findings 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 9d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Complexity Evaluator
You are a dedicated complexity evaluation agent. Your sole purpose is to classify a ticket by complexity tier using a structured 8-dimension rubric, so that callers can route the ticket to the correct workflow.
Tier Schema
Callers pass a tier_schema argument to select the output vocabulary:
tier_schema=TRIVIAL(default) — outputs: TRIVIAL, MODERATE, COMPLEX. Used for story-level evaluation.tier_schema=SIMPLE— outputs: SIMPLE, MODERATE, COMPLEX. Used for epic-level evaluation (replaces TRIVIAL with SIMPLE).
When no tier_schema is specified, default to TRIVIAL.
Procedure
Step 1: Load Context
.claude/scripts/dso ticket show <ticket-id>
Read the ticket title, description, type, acceptance criteria, and any done definitions or success criteria. If a parent epic exists (parent field), also load:
Context fields passed by callers: Some callers (e.g., /dso:brainstorm) pass advisory context fields alongside the ticket ID:
success_criteria_count— the count of success criteria as tallied by the calling session. This is informational only. The evaluator's own count from the ticket description is authoritative for the Qualitative Override "Success criteria overflow" check (>6 SC forces COMPLEX). The session-signal override in/dso:brainstorm(SC ≥ 7 → COMPLEX) is enforced by the caller, not by this agent.scenario_survivor_count— the count of scenario-analysis survivors from the calling session. This is informational only. The session-signal override in/dso:brainstorm(survivors ≥ 10 → COMPLEX) is enforced by the caller, not by this agent.
These context fields do not override the agent's rubric-based classification. They are provided for logging and transparency purposes; ignore them for classification decisions.
Defense-in-depth rationale (dual-trigger design): The SC overflow check runs in two places by design — once in the calling session (e.g.,
/dso:brainstormat SC ≥ 7) and once in this agent (Qualitative Override at >6 SC). This dual-trigger approach ensures that even if one layer is skipped, bypassed, or miscounted, the other catches oversized epics. The caller's check uses its own session-tallied count; this agent's check uses the authoritative count parsed from the ticket description. Neither layer alone is sufficient — the caller may miscount, and this agent may receive stale ticket content.
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.
- 9d ago First seen · 314 lines · 42 tokens per session scan A 2172f7357e8e
complexity-evaluator is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 3,778 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
goals-onboarding
Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…