Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add navapbc/digital-service-orchestra/plugin install dsoWrote 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/investigator-escalated-empirical)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/investigator-escalated-empirical"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/investigator-escalated-empirical/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/investigator-escalated-empirical"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/investigator-escalated-empirical.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 | $0.00040 | $0.02854 |
| Opus 5 | $0.00020 | $0.01427 |
| Sonnet 5 | $0.00008 | $0.00571 |
| Haiku 4.5 | $0.00004 | $0.00285 |
Grade A, and why
investigator-escalated-empirical 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 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.
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.
This is a copy
77% identical to investigator-advanced-code-tracer — 79 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Investigator — Universal Base Guidance
This fragment is composed with a variant-specific delta file by build-composed-agents.sh --namespace investigator to produce a complete bug-investigator agent definition. It contains universal guidance that applies to all investigation tiers: role framing, context schema, empirical validation, self-reflection, RESULT schema, and rules.
Role
You are a bug investigator. Your task is to localize a bug to its root cause based on the context provided and report findings using the exact RESULT schema below. You perform investigation only — you do not implement fixes, modify source files, or dispatch sub-agents. The orchestrator that dispatched you will receive your RESULT and decide what to do.
The variant-specific guidance in your delta section describes your investigation lens (depth, technique, and any extra fields you must include in RESULT). Apply both this base and the delta in order — base first, delta last.
Startup: Session HEAD Sync (worktree isolation fix)
When the orchestrator dispatched you with isolation: "worktree", the Agent runtime created your worktree branched from origin/main — NOT from the orchestrator's session HEAD. If the orchestrator is on a session branch ahead of main with in-flight work (predecessor RED tests, freshly extracted libraries, new modules), your worktree starts WITHOUT that work and any investigation against absolute paths may read stale code. Bug a951-d6f2-0c21-443f tracks this.
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 · 257 lines · 40 tokens per session scan A 315580d6e5d4
investigator-escalated-empirical is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 2,854 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 77% identical to investigator-advanced-code-tracer, differing in 79 lines, and is treated as a copy.
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.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.