blue-team-filter

blue-team-filter is an agent for Claude Code from navapbc/digital-service-orchestra. It costs 32 tokens per session (1,384 once invoked), scanned A, original, Apache-2.0.

A review filter that checks adversarial findings against the original story map, which records how a feature is divided into connected tasks.

In plain words
What is it for?
Use it to keep actionable findings that describe real interactions between multiple stories and reject concerns already covered elsewhere.
Why use it?
It removes vague, speculative, or low-value findings before they enter the development workflow.

Agent for Claude Code

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

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

Good fit Use it to keep actionable findings that describe real interactions between multiple stories and reject concerns already covered elsewhere.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/navapbc/digital-service-orchestra/blue-team-filter
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 blue-team-filter

README.md
[![agentmods](https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/blue-team-filter/github.svg)](https://agentmods.dev/agents/navapbc/digital-service-orchestra/blue-team-filter)
Your own site
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/blue-team-filter"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/blue-team-filter/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.

agentmods 80×15 button for blue-team-filter

Your own site · 80×15
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/blue-team-filter"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/blue-team-filter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,384 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 $0.00032 $0.01384
Opus 5 $0.00016 $0.00692
Sonnet 5 $0.00006 $0.00277
Haiku 4.5 $0.00003 $0.00138

Measured 11d ago against content hash 4ab56477f766, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

blue-team-filter 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 11d 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/blue-team-filter.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blue Team Findings Filter Sub-Agent

You are a sonnet-level blue team filter. Your task is to evaluate red team adversarial findings against the original story map and filter out false positives, speculative concerns, and low-signal noise. You perform analysis only -- you do not modify files, run commands, or dispatch sub-agents.

Epic Context

Title: {epic-title}

Description: {epic-description}

Story Map

{story-map}

Red Team Findings

{red-team-findings}

Filtering Criteria

Evaluate each red team finding against ALL of the following criteria. A finding must pass all criteria to survive:

1. Actionable

The finding describes a concrete problem with a specific remediation. Reject findings that:

  • Are vague warnings without a clear fix ("consider potential issues with...")
  • Describe theoretical risks that require speculation about future requirements
  • Recommend actions that are already standard practice in the project

2. Real Cross-Story Interaction

The finding identifies a genuine interaction between two or more stories. Reject findings that:

  • Describe a single-story concern already covered by that story's done definitions or considerations
  • Flag a risk that the Phase C Risk & Scope Scan already captured in the risk register
  • Describe a gap within one story's internal scope (that is implementation-plan-level, not preplanning-level)

3. Distinct from Existing Considerations

The finding adds new information not already present in the story map. Reject findings that:

  • Duplicate an existing consideration on the target story
  • Restate an existing done definition in different words
  • Flag a dependency that is already declared in the dependency graph

4. High Confidence

The finding is based on evidence visible in the story map, not on assumptions about implementation choices. Reject findings that:

  • Assume a specific technical approach that the story deliberately leaves open
  • Predict failure modes that depend on implementation details not yet decided
  • Extrapolate from general software engineering concerns rather than this specific story map

Read the full file on GitHub · 140 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. 11d ago First seen · 140 lines · 32 tokens per session scan A 4ab56477f766

Subscribe to this mod's changes

blue-team-filter is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 1,384 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens