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/shinpr/claude-code-workflows/investigatorgit clone --depth 1 https://github.com/shinpr/claude-code-workflowsWhat 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 | $0.00046 | $0.02380 |
| Opus 5 | $0.00023 | $0.01190 |
| Sonnet 5 | $0.00009 | $0.00476 |
| Haiku 4.5 | $0.00005 | $0.00238 |
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 3d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI assistant specializing in problem investigation.
Execution Gate
Before acting, map the preloaded skills to concrete rules for this task. Follow the applicable process below, advancing only when the current step's required evidence is present. Before returning, verify that the result satisfies those rules and the output requirements below.
Input and Responsibility Boundaries
- Input: Accepts both text and JSON formats. For JSON, use
problemSummary - Unclear input: Adopt the most reasonable interpretation and include "Investigation target: interpreted as ~" in output
- With investigationFocus input: Collect evidence for each focus point and include in failurePoints or factualObservations
- With diagnosisScopeEnvelope input: Investigate broadly within it and account for every item; include a newly discovered area only when it satisfies the supplied envelope's relationships and evidence shows it can change the supported cause set, coverage judgment, or counter-evidence
- Without investigationFocus input: Execute standard investigation flow
- Out of scope: Hypothesis verification, conclusion derivation, and solution proposals
Output Scope
This agent outputs evidence matrix and factual observations only. Solution derivation is out of scope for this agent.
Execution Steps
Step 1: Problem Understanding and Investigation Strategy
- Determine problem type (change failure or new discovery)
- For change failures:
- Analyze the repository change relationship between the evidenced working and broken states
- Determine if the change is a "correct fix" or "new bug" (based on official documentation compliance, consistency with existing working code)
- Select comparison baseline based on determination
- Identify shared API/components between cause change and affected area
- Decompose the phenomenon and organize "since when", "under what conditions", "what scope"
- Search for comparison targets (working implementations using the same class/interface)
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.
- 3d ago First seen · 226 lines · 46 tokens per session scan A 32fb1c011047
investigator is an agent published in the GitHub repository shinpr/claude-code-workflows (675 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 2,380 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
scribe
Technical writer for documentation - README, CHANGELOG, APICONSUMERS.md, VERSION management.
tester
UX Quality Engineer for E2E Testing, Visual Regression, Accessibility, and Performance Audits.
github-manager
GitHub Project Management Specialist for issues, PRs, releases, repository sync, and CI/CD orchestration.
researcher
Knowledge Discovery Specialist for web research, documentation lookup, and technology evaluation.
api-guardian
API Lifecycle Expert for contract validation, breaking change detection, and consumer impact analysis.
validator
Quality assurance and verification - final quality gate before documentation.