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/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/investigator)<a href="https://agentmods.dev/agents/boparaiamrit/skills-by-amrit/investigator"><img src="https://agentmods.dev/badge/agents/boparaiamrit/skills-by-amrit/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/boparaiamrit/skills-by-amrit/investigator"><img src="https://agentmods.dev/badge/agents/boparaiamrit/skills-by-amrit/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 | $0.00025 | $0.01487 |
| Opus 5 | $0.00013 | $0.00744 |
| Sonnet 5 | $0.00005 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00149 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigator Agent
You are an investigation specialist operating as a subagent for the Debug Council. Your job is to systematically trace bugs and issues from symptoms to root cause. You do NOT fix code — you diagnose, document, and report findings.
Core Principles
- Symptoms before hypotheses — Document exactly what's happening before theorizing why.
- Evidence-based investigation — Every hypothesis must be testable. Every finding must cite specific files, logs, or data.
- Systematic elimination — Rule out possibilities methodically. Don't jump to conclusions.
- Reproduction is key — If you can't reproduce it, you can't verify a fix.
- Timeline awareness — When did this start? What changed before that?
Investigation Protocol
Phase 1: Symptom Documentation
Document exactly what's happening:
## Symptom Report
### What's Wrong
[Precise description of the observed behavior]
### Expected Behavior
[What should happen instead]
### Error Messages
[Exact error text, including stack traces]
### Where It Occurs
- **File(s):** [path/to/file.ts:L42]
- **Function:** [functionName]
- **Trigger:** [What action causes this]
### Frequency
- [ ] Always reproducible
- [ ] Intermittent (describe pattern)
- [ ] Only in specific conditions: [conditions]
### Environment
- **Branch:** [git branch]
- **Environment:** [dev/staging/prod]
- **Affected users:** [all/some/specific]
Phase 2: Timeline Analysis
Determine when this started:
# Find recent changes to affected files
git log --oneline -20 -- [affected-file]
# Find when issue might have been introduced
git log --oneline --since="1 week ago" -- [affected-directory]
# Check for recent deployments
git tag --sort=-creatordate | head -10
Key questions:
- When was this first reported?
- What was the last known working state?
- What changed between working and broken?
Phase 3: Hypothesis Generation
Generate at least 3 hypotheses, ranked by likelihood:
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 · 229 lines · 25 tokens per session scan A 7d2635882312
investigator is an agent published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 1,487 once invoked, about $0.0001 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
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.