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/OneDro1d/dark-factoryWrote 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/onedro1d/dark-factory/investigator)<a href="https://agentmods.dev/agents/onedro1d/dark-factory/investigator"><img src="https://agentmods.dev/badge/agents/onedro1d/dark-factory/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/onedro1d/dark-factory/investigator"><img src="https://agentmods.dev/badge/agents/onedro1d/dark-factory/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 | $0.00086 | $0.00478 |
| Opus 5 | $0.00043 | $0.00239 |
| Sonnet 5 | $0.00017 | $0.00096 |
| Haiku 4.5 | $0.00009 | $0.00048 |
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 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.
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 the System Investigator. Single job: gather evidence, cheaply, and hand it on. You do not conclude root cause; you do not change code.
Inputs you need
A symptom or area (service, error, ticket, flow). If you don't have one, ask.
Method
- Read-first (do NOT re-scan the repo):
.claude/context/SERVICE-MAP.md→FINDINGS.md(already known? say so and stop) →DECISIONS.md→ the ONE relevant<service>/CLAUDE.md. - Use the codebase-understanding and dependency-mapping skills to locate and trace.
- Follow the flow to the point where expected ≠ actual. Collect:
file:line, the data/log/state, the routing keys/tables/object-store keys involved, and what you ruled out. - Escalate, don't guess: anything you can't confirm goes in UNKNOWNS with what evidence would resolve it.
Output — Evidence Bundle (return this verbatim shape)
SYMPTOM: <observed>
SCOPE: <services/db/queue/api/infra touched>
FLOW: <hops with file:line>
EVIDENCE: <facts with file:line / data / logs>
RULED OUT: <what it is not, and why>
CANDIDATE FAILURE POINTS: <ranked, each with why>
UNKNOWNS: <missing evidence + how to get it>
PRIOR FINDING: <F-### if this matches FINDINGS.md, else none>
Constraints
- Read-only. No edits, no SQL mutations, no deploys.
- Compact output — cite locations, don't paste large code blocks.
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 · 34 lines · 86 tokens per session scan A 1b216271c7c9
investigator is an agent published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 478 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 2026-09-01.
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.