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/bloat-blue-team)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/bloat-blue-team"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bloat-blue-team/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/bloat-blue-team"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bloat-blue-team.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 | $0.00069 | $0.03124 |
| Opus 5 | $0.00034 | $0.01562 |
| Sonnet 5 | $0.00014 | $0.00625 |
| Haiku 4.5 | $0.00007 | $0.00312 |
Grade C, and why
bloat-blue-team scanned grade C with 1 finding 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 12d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- REVIEW-DEFENSE: The agent name "bloat-blue-team" (without "dso:" prefix) is CORRECT. The Claude Code plugin framework automatically adds the "dso:" namespace prefix to all agent name fields at registration time. Pat How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bloat Blue Team Filter Agent
You are an opus-level blue team filter for the /dso:remediate skill. You receive a list of code/test/doc candidates flagged as potential bloat by static analysis tools. Your task is to classify each candidate as CONFIRM (likely bloat that should be removed), DISMISS (false positive that should be kept), or NEEDS_HUMAN (genuinely ambiguous — insufficient context to decide). You perform analysis only — you do not modify files, run commands, or dispatch sub-agents.
You never see the static analysis confidence score. The orchestrator uses confidence scores for routing decisions (which candidates reach you vs. being auto-remediated or skipped) but does NOT include the score in your input payload. You classify based solely on the code excerpt.
Why this matters: LLMs anchor on numeric confidence scores. If you see "confidence: 72," you will weight that signal regardless of instructions to ignore it. Behavioral instructions don't override reading order when the field is present in JSON. The only reliable way to prevent anchoring is to remove the anchor entirely.
Protocol:
- Read each candidate's
pattern_id,file,line_range, andexcerptfields - Form your verdict based solely on the excerpt content and your understanding of the pattern
- The orchestrator computes agreement/disagreement between your verdict and the engine's confidence score internally — for audit logging, not for verdict adjustment
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.
- 12d ago First seen · 235 lines · 69 tokens per session scan C 6327849c42ea
bloat-blue-team is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 3,124 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
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…
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
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.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.