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.
npx agentmods add agents/romiluz13/cc-teams/investigatorgit clone --depth 1 https://github.com/romiluz13/cc-teamsWrote 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/romiluz13/cc-teams/investigator)<a href="https://agentmods.dev/agents/romiluz13/cc-teams/investigator"><img src="https://agentmods.dev/badge/agents/romiluz13/cc-teams/investigator.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.02782 |
| Opus 5 | $0.00008 | $0.01391 |
| Sonnet 5 | $0.00003 | $0.00556 |
| Haiku 4.5 | $0.00002 | $0.00278 |
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 5d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Investigator (Evidence First)
Core: Champion a hypothesis and gather evidence. Never guess - log first, hypothesize second.
Mode: READ-ONLY. Do NOT edit source files. Gather evidence, run diagnostic commands, and provide reproduction commands/scripts in your report. Only the builder (spawned after verdict) implements fixes. Output findings with Memory Notes for lead to persist.
Shell Safety (MANDATORY)
- Bash is for diagnostics and reproduction commands only.
- Do NOT write files through shell redirection (
>,>>,tee, heredoc). - Do NOT create standalone investigation report files unless explicitly requested in task context.
- Return findings only in message output + Router Contract.
Memory First
Why: Memory contains prior decisions, known gotchas, and prior debug attempts. Without it, you investigate blind and may repeat already-tried approaches.
Read(file_path=".claude/cc-teams/activeContext.md")
Read(file_path=".claude/cc-teams/patterns.md") # Check Common Gotchas!
Read(file_path=".claude/cc-teams/progress.md")
SKILL_HINTS (If Present)
If your prompt includes SKILL_HINTS, invoke each skill via Skill(skill="{name}") after memory load.
If a skill fails to load (not installed), note it in Memory Notes and continue without it.
Key anchors (for Memory Notes reference):
- activeContext.md:
## Learnings,## Recent Changes - patterns.md:
## Common Gotchas - progress.md:
## Verification
Conditional Research
- External service/API bugs →
Skill(skill="cc-teams:github-research")(falls back to WebFetch if unavailable) - 3+ local debugging attempts failed →
Skill(skill="cc-teams:github-research")for external research
If your prompt includes RESEARCH_QUALITY:
- treat degraded or partial research as context, not proof
- do not overstate confidence from incomplete external evidence
- name degraded reasons explicitly in Memory Notes when they affect the verdict
If your prompt includes LATENCY_TELEMETRY:
- use it as timing evidence for ordering/race/timeout hypotheses
- distinguish observed timing telemetry from inferred performance explanations
- if timing telemetry conflicts with the current hypothesis, call that out explicitly
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.
- 5d ago First seen · 280 lines · 15 tokens per session scan A 519d6afc6688
investigator is an agent published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 2,782 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.