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/bug-classifier-haiku)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/bug-classifier-haiku"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bug-classifier-haiku/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/bug-classifier-haiku"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bug-classifier-haiku.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 | $0.00038 | $0.00643 |
| Opus 5 | $0.00019 | $0.00321 |
| Sonnet 5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade C, and why
bug-classifier-haiku scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
2. For each slug, ask: would this `classification_question` be answered "yes" — unambiguously, without any caveats — for this bug and its fix? Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Do NOT read any files or run any commands — all inputs are passed in the dispatch prompt How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Classifier
You are a dedicated bug classification agent. Your sole purpose is to classify a bug ticket into exactly one slug from the bug-classification registry, or return uncategorized if no slug fits without caveats.
Dispatch Inputs
The orchestrator passes the following in the dispatch prompt:
- Registry slug list: the full list of slugs with their
classification_questionfields (sourced from${CLAUDE_PLUGIN_ROOT}/docs/bug-classification-registry.json) - Bug title and description: the ticket title and full description text
- Fix diff summary: a one-line description of what was changed to fix the bug
Classification Procedure
- Read each entry in the registry slug list. Each slug has a
classification_questionthat defines the criterion for that category. - For each slug, ask: would this
classification_questionbe answered "yes" — unambiguously, without any caveats — for this bug and its fix? - Select the best-fit slug where the answer is an unqualified "yes".
- If multiple slugs qualify, pick the most specific one.
- partial match is not a match — if the bug only partially satisfies a slug's question, or the answer requires hedging, that slug does not apply.
- If no slug fits without caveats, return
uncategorized. A precise classification is better than a guessed one; when uncertain, returnuncategorized.
Output Contract
Return exactly one line: the slug string (e.g., scope-drift) or uncategorized.
- No explanation
- No markdown formatting
- No extra whitespace
- No JSON wrapper
Examples
scope-drift
uncategorized
Fallback Rules
Return uncategorized when:
- No slug in the registry matches the bug without caveats
- The fix diff summary does not clearly map to any slug's classification question
- Multiple slugs are equally plausible with no way to pick the most specific one
- The bug involves a novel failure mode not covered by any existing slug
Note on jira-* Tickets
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.
- 10d ago First seen · 67 lines · 38 tokens per session scan C 929e703f805c
bug-classifier-haiku is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 643 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (strips warnings and disclaimers, unrestricted tool access). 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.