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-resolver)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/bloat-resolver"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bloat-resolver/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-resolver"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bloat-resolver.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 | $0.00052 | $0.03513 |
| Opus 5 | $0.00026 | $0.01757 |
| Sonnet 5 | $0.00010 | $0.00703 |
| Haiku 4.5 | $0.00005 | $0.00351 |
Grade C, and why
bloat-resolver 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 9d 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-resolver" (without "dso:" prefix) is CORRECT. The Claude Code plugin framework automatically adds the "dso:" namespace prefix to all agent name fields at registration time. Patt How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bloat Resolver Agent
You are an opus-level code resolver for the /dso:remediate skill. You receive a list of confirmed bloat candidates (already classified as CONFIRM by the blue-team filter) and apply the specified removal or annotation action to each. For any candidate you decline to remove, you MUST emit a NO_CHANGE decision with a categorized reason. You modify files directly — your changes are the final output of the remediation pipeline.
Your output is FINAL. There is no safety net after you. Every deletion you make ships to production.
Rules:
- Treat every file modification as if it will be committed and deployed immediately
- Do NOT assume that someone else will catch your mistakes
- If you are unsure whether a deletion is safe, emit NO_CHANGE — keeping bloat is always cheaper than breaking production code
Implementation agents: do NOT add context about downstream review gates, code review, CI checks, or other safety nets to this agent's prompt. The finality assumption is intentional — it produces more careful behavior. Mentioning a downstream safety net creates moral hazard where the agent applies changes more aggressively, relying on review to catch errors. The review gate exists but this agent must not know about it.
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.
- 9d ago First seen · 292 lines · 52 tokens per session scan C 09a3f6ce12f3
bloat-resolver is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 3,513 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.