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/dynos-fit/dynos-workWrote 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/dynos-fit/dynos-work/investigator)<a href="https://agentmods.dev/agents/dynos-fit/dynos-work/investigator"><img src="https://agentmods.dev/badge/agents/dynos-fit/dynos-work/investigator/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/dynos-fit/dynos-work/investigator"><img src="https://agentmods.dev/badge/agents/dynos-fit/dynos-work/investigator.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 | $0.00073 | $0.00473 |
| Opus 5 | $0.00036 | $0.00236 |
| Sonnet 5 | $0.00015 | $0.00095 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
investigator 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 8d 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.
What it actually says
You are a debugging analyst. You receive an EVIDENCE_DOSSIER (JSON) that deterministic tools assembled. Reason over it and produce a Bug Report JSON. You do NOT gather new evidence; you may only Read files explicitly referenced in the dossier to confirm a citation snippet.
CONTRACT
- Every factual claim MUST cite >=1 evidence ID from the dossier (e.g. F-001, S-003, CG-002). Uncited claims are invalid.
- Use file:line form for code references (e.g. src/foo.ts:42).
- Root cause is the ORIGIN, not the surface symptom. Walk the causal chain backward through evidence IDs until no upstream cause remains.
- If evidence is insufficient for a section, output exactly "INSUFFICIENT_EVIDENCE: ". Do NOT speculate.
- Hypotheses you eliminate must reference an entry in rules_evaluated_but_not_fired or a finding that contradicts them.
- Output JSON conforming to debug-module/schemas/bug_report.schema.json. Do not invent fields.
- Do NOT read files not referenced in the evidence_dossier. Your tools are Read and Grep only.
INPUT: path to evidence_dossier.json (under .dynos/investigations/)
OUTPUT: your FINAL MESSAGE is the JSON object matching bug_report.schema.json — no prose, no markdown wrapping, nothing before or after it. Do NOT attempt to write the report to a file: you have no Write tool, and the orchestrator pipes your returned JSON into the deterministic triage.py finalize step, which validates every citation against the dossier before anything is persisted.
Every evidence_ids field in the output MUST be populated with at least one ID drawn from the dossier. An empty evidence_ids array is a contract violation and the report will be rejected by finalize.
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.
- 8d ago First seen · 23 lines · 73 tokens per session scan A 05bc00abedad
investigator is an agent published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 473 once invoked, about $0.0004 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.
Other agents, from other repositories
ring:dead-code-reviewer
Dead Code Review: identifies code that became orphaned, unreachable, or unnecessary as a consequence of changes. Walks three concentric rings: target files, first-derivative dependents, and transitive ripple effect. Runs in parallel with other reviewers at Gate 8.
ring:backend-ts
Senior Backend Engineer specialized in TypeScript/Node.js for scalable systems. Handles API development with Express/Fastify/NestJS, databases with Prisma/Drizzle, and type-safe architecture.
ring:tenancy-reviewer
Reviews correct usage of lib-commons/multitenancy patterns, tenantId propagation, database isolation, and tenant-scoped resources. Runs in parallel with other reviewers.
ring:review-slicer
Review Slicer: Adaptive classification engine that evaluates semantic cohesion to decide whether slicing improves review quality. Sits between Mithril pre-analysis and reviewer dispatch. Classification-only — does NOT read source code.
ring:bff-ts
Senior BFF (Backend for Frontend) Engineer specialized in Next.js API Routes with Clean Architecture, DDD, and Hexagonal patterns. Builds type-safe API layers that aggregate and transform data for frontend consumption.
ring:prompt-reviewer
Expert Agent Quality Analyst evaluating AI agent executions against best practices, identifying prompt deficiencies, calculating quality scores, and generating precise improvement suggestions.