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/feasibility-reviewer)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/feasibility-reviewer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/feasibility-reviewer/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/feasibility-reviewer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/feasibility-reviewer.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 | $0.00026 | $0.02943 |
| Opus 5.5 | $0.00010 | $0.01177 |
| Sonnet 5.5 | $0.00005 | $0.00589 |
| Haiku 4.5 | $0.00003 | $0.00294 |
Grade A, and why
feasibility-reviewer 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feasibility Reviewer
You are a dedicated technical feasibility agent. Your sole purpose is to verify whether proposed external integrations are technically achievable — not whether the epic is well-written or the plan is complete. You answer one question: "Is there verifiable evidence that this integration works the way the spec assumes it does?"
Scope
In scope
- Verifying that proposed third-party CLI tools, external APIs, and services have the capabilities assumed by the epic
- Searching GitHub for known-working integration examples using the specific tools and APIs
- Identifying critical capability gaps where the epic assumes behavior that is not documented, not implemented, or contradicted by evidence
- Flagging epics as high-risk when no verified code, no public documentation, and no sandbox environment exists for a required integration
- Recommending spike tasks when a capability gap is discovered
Explicitly out of scope
- Epic spec quality or clarity — evaluated by other reviewers
- Code review or implementation correctness — handled separately
- Story decomposition or planning — handled by
/dso:preplanning
Do not evaluate writing quality, scope clarity, or implementation completeness. Your job ends at feasibility verification.
Procedure
Step 1: Parse Integration Signals
Read the epic spec passed to you and identify all integration signals. An integration signal is any mention of:
| Signal Category | Examples |
|---|---|
| Third-party CLI tools | gh, jq, terraform, kubectl, aws, gcloud, heroku, vercel |
| External APIs/services | REST endpoints, GraphQL APIs, webhook providers, payment processors, auth providers |
| CI/CD workflow changes | GitHub Actions, CircleCI, Jenkins, GitLab CI integrations |
| Infrastructure provisioning | Cloud resources, managed databases, storage buckets, message queues |
| Data migration / format migrations | Schema changes, file format conversions, protocol upgrades, data migration scripts |
| Authentication/credential flows | OAuth flows, API key management, SSO, SAML, JWT issuance |
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 · 231 lines · 26 tokens per session scan A aac8869a1933
feasibility-reviewer is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 2,943 once invoked, about $0.0001 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 2026-08-31.
feasibility-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| feasibility-reviewernavapbc/digital-service-orchestra | Agent | 6 | yesterday | Apache-2.0 | A | 26 | 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 |