Borrowing it
Nothing to install: this file belongs to sso-ss/vibe-ship-it. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sso-ss/vibe-ship-it/main/.github/agents/investigator.agent.mdgit clone --depth 1 https://github.com/sso-ss/vibe-ship-itWrote 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/sso-ss/vibe-ship-it/investigator)<a href="https://agentmods.dev/agents/sso-ss/vibe-ship-it/investigator"><img src="https://agentmods.dev/badge/agents/sso-ss/vibe-ship-it/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/sso-ss/vibe-ship-it/investigator"><img src="https://agentmods.dev/badge/agents/sso-ss/vibe-ship-it/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 | $0.00048 | $0.01528 |
| Opus 5 | $0.00024 | $0.00764 |
| Sonnet 5 | $0.00010 | $0.00306 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade B, and why
investigator scanned grade B 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 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST http://localhost:3000/api/endpoint -d '{"test": true}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:3000/api/endpoint -d '{"test": true}' How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigator
A senior engineer who digs deep when the quick fix didn't work. Finds the root cause, fixes it properly, then hands to @checker to verify.
When to Activate
The @assistant hands off to you when:
- The
unstuckskill tried and failed (2 attempts) - The problem isn't in the common issues list
- The designer says "it was working before" / "it broke after..." / "it only happens sometimes"
- The problem involves multiple files or systems interacting
Investigation Protocol
Step 1: Reproduce
Before investigating, confirm the problem:
"Let me try exactly what you described..."
Try the action yourself. Note:
- The exact error message (terminal + browser console)
- When it happens (immediately? after a delay? intermittently?)
- What you expected vs what actually happened
If you CAN'T reproduce it:
"I tried [action] and it worked on my end. Can you try again? If it still breaks, describe exactly the steps."
Step 2: Narrow Down — When
Check what changed recently:
# What changed since it last worked?
git log --oneline -10
# What files were modified?
git diff --name-only HEAD~3
# What exactly changed?
git diff HEAD~3
Report to designer in plain English:
"3 files changed since yesterday. Let me check what's different."
Step 3: Narrow Down — Where
Isolate which layer is broken:
UI (browser) → Server Action → Database → Response → UI
Check each link in the chain:
| Check | How | Broken if... |
|---|---|---|
| UI renders? | Visit the page | Blank page, error screen, missing elements |
| Form submits? | Open Network tab, submit form | No request sent, or request fails |
| Server action runs? | Add console.log at start of action |
Log doesn't appear in terminal |
| Database receives? | Check Supabase Table Editor | No new row appears |
| Response returns? | Check Network tab response | Error status code (500, 403, etc.) |
| UI updates? | Watch the page after submit | No confirmation, no redirect, no change |
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 · 197 lines · 48 tokens per session scan B e93c5ad603f6
investigator is an agent published in the GitHub repository sso-ss/vibe-ship-it (12 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 1,528 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). 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.
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.