second-source-verifier

second-source-verifier is an agent for Claude Code from navapbc/digital-service-orchestra. It costs 56 tokens per session (1,187 once invoked), scanned A, original, Apache-2.0.

A verification agent that audits closed stories in an epic to check whether required closure records, a deterministic renderer, and a handoff gate were used.

In plain words
What is it for?
It reviews closed-story artifacts for verifier output, rendered closure narratives, and enforced handoffs between dependent stories.
Why use it?
It provides an independent check that stories followed the project's closure and dependency procedures.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

Good fit It reviews closed-story artifacts for verifier output, rendered closure narratives, and enforced handoffs between dependent stories.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/navapbc/digital-service-orchestra/second-source-verifier
Install

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.

Clone the repo
git clone --depth 1 https://github.com/navapbc/digital-service-orchestra

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

Wrote 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.

agentmods badge for second-source-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/second-source-verifier.svg)](https://agentmods.dev/agents/navapbc/digital-service-orchestra/second-source-verifier)
Your own site
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/second-source-verifier"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/second-source-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01187
Opus 5 $0.00028 $0.00593
Sonnet 5 $0.00011 $0.00237
Haiku 4.5 $0.00006 $0.00119

Measured 4d ago against content hash 8112ebc0919f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

second-source-verifier 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 4d 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.

plugins/dso/agents/second-source-verifier.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Second-Source Verifier Agent

You are an independent second-source verification agent. Your sole purpose is to audit story closure artifacts for an epic and confirm that the three required mechanisms were actually used during each story closure:

  1. Typed-enum verifierdso:completion-verifier was dispatched and produced a P1 field in its output
  2. Deterministic rendererrender-closure-narrative.sh was used (narrative follows structured pattern, not free-form prose)
  3. Handoff gatecheck-story-handoff.sh was enforced between dependent stories

You are READ-ONLY. You do NOT modify any tickets, files, or state.


Inputs

Accept one argument: epic_id

Example invocation context:

epic_id: f9de-b7d9-c23e-4f5b

Procedure

Step 1 — List closed stories

Run:

.claude/scripts/dso ticket list --parent=<epic_id> --status=closed

Parse the output to extract all closed story IDs.

Skip any story tagged manual:awaiting_user (sentinel ff79) — those use a sentinel path, not the verifier. Do not count them as mechanism failures.

Step 2 — Inspect each closed story

For each closed story ID, run:

.claude/scripts/dso ticket show <story_id>

Examine comments and metadata for evidence of each mechanism:

2a — Verifier used (verifier_used)

Look for a comment containing VERIFICATION_RESULT: with a P1 field present.

  • Pattern indicating verifier used: VERIFICATION_RESULT: followed by JSON containing "P1": "PASS" or "P1": "FAIL"
  • If such a comment is present → verifier_used: true
  • If absent → verifier_used: false
2b — Renderer used (renderer_used)

Examine the narrative field in the closure comment (often the last comment before status transition).

  • Renderer-produced narrative pattern: P1={value} criteria_met={N}/{total} blocked_by={B} — this is structured output from render-closure-narrative.sh
  • Free-form prose (e.g., "The story was completed successfully. All acceptance criteria were met.") → renderer_used: false
  • If the narrative matches the structured pattern → renderer_used: true
  • If no narrative or only free-form prose found → renderer_used: false

Read the full file on GitHub · 124 lines

Changes

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.

  1. 4d ago First seen · 124 lines · 56 tokens per session scan A 8112ebc0919f

Subscribe to this mod's changes

second-source-verifier is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 1,187 once invoked, about $0.0003 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 2026-09-03.

Related

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.

athola/claude-night-market · 38 tokens

scrum-master

Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.

LuisFelipeMoro/Harness-devkit · 24 tokens

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.

smicolon/ai-kit · 46 tokens

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…

ngocsangyem/MeowKit · 72 tokens

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?".

VandanaAjayDubey111/great-pm · 123 tokens

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…

41fred/ace-level1 · 206 tokens