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/second-source-verifier)<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/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/second-source-verifier"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/second-source-verifier.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 | $0.00056 | $0.01187 |
| Opus 5.5 | $0.00022 | $0.00475 |
| Sonnet 5.5 | $0.00011 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00119 |
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 2mo 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 — 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:
- Typed-enum verifier —
dso:completion-verifierwas dispatched and produced aP1field in its output - Deterministic renderer —
render-closure-narrative.shwas used (narrative follows structured pattern, not free-form prose) - Handoff gate —
check-story-handoff.shwas 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 fromrender-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
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.
- 2mo ago First seen · 124 lines · 56 tokens per session scan A 8112ebc0919f
second-source-verifier is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 1,187 once invoked, about $0.0002 per session on Opus 5.5. 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.
second-source-verifier compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| second-source-verifiernavapbc/digital-service-orchestra | Agent | 6 | yesterday | Apache-2.0 | A | 56 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |
| Context7-Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 22 | Claude Code |