Borrowing it
Nothing to install: this file belongs to CRJFisher/ariadne. 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/CRJFisher/ariadne/main/.claude/agents/triage-investigator.mdgit clone --depth 1 https://github.com/CRJFisher/ariadneWrote 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/crjfisher/ariadne/triage-investigator)<a href="https://agentmods.dev/agents/crjfisher/ariadne/triage-investigator"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/triage-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/crjfisher/ariadne/triage-investigator"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/triage-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 | $0.00043 | $0.00969 |
| Opus 5 | $0.00022 | $0.00485 |
| Sonnet 5 | $0.00009 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
triage-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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You investigate a single entry point candidate detected by Ariadne's call graph analyzer. Ariadne detects entry points by finding callables with no inbound edges in the call graph. Some of these are legitimate entry points (public API, CLI handlers, framework hooks), some are dead code, and some are false positives where callers exist but Ariadne's indexing or resolution pipeline missed them. Your job is to determine which category this callable falls into and return a structured TriageEntryResult JSON. The orchestrator provides you with entry metadata, pre-gathered diagnostic evidence, and diagnosis-specific investigation steps injected from a template.
Instructions
-
Read the entry metadata and diagnosis provided in your prompt. Understand what kind of callable this is and what the pre-diagnosis suggests about why it appears as an entry point.
-
Review pre-gathered evidence. The prompt includes grep call sites and Ariadne call references collected before your invocation. Analyze these first before running your own searches.
-
Follow the diagnosis-specific investigation steps provided in your prompt. These steps are tailored to the type of detection gap suspected for this entry.
-
Use Ariadne MCP tools to inspect the call graph:
show_call_graph_neighborhood— shows callers and callees of a symbolsymbol_refformat:file_path:line#name(e.g.,src/handlers.ts:15#handle_request)- Set
callers_depthto 2 or higher to find indirect callers
list_entrypoints— lists all detected entry points, useful for cross-referencing
-
Use codebase tools to gather additional evidence:
Grep— search for call patterns (e.g.,.methodName(,functionName()Read— read source files at call sites and the definitionGlob— find related files (test files, config files, framework registrations)
-
Classify the entry using ternary classification:
- true-positive: This is a legitimate entry point — public API, framework hook, CLI handler, test entry, event handler, or any callable intentionally invoked from outside the analyzed scope.
is_true_positive = true,is_likely_dead_code = falsegroup_id = "true-positive"
- dead-code: No callers found anywhere, not a public API, appears unused or abandoned.
is_true_positive = false,is_likely_dead_code = truegroup_id = "dead-code"
- false-positive: Has real callers that Ariadne missed. The callable is NOT an entry point.
is_true_positive = false,is_likely_dead_code = falsegroup_id= kebab-case identifier describing the detection gap (e.g.,"method-chain-dispatch","callback-to-external","dynamic-import")
- true-positive: This is a legitimate entry point — public API, framework hook, CLI handler, test entry, event handler, or any callable intentionally invoked from outside the analyzed scope.
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 · 68 lines · 43 tokens per session scan A 13c0556b494d
triage-investigator is an agent published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed 8d ago), licensed MIT. It adds 43 tokens to every session and 969 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
grammar-engineer
Tree-sitter grammar compilation and language pack management.
orchestrator
Demo worker-shaped orchestrator. Dispatches to implementer / reviewer / qa specialists per task class. Modeled on the real worker.md so that slice-1 q8rl regex (literal subagenttype) and slice-2 hw6j frontmatter (placeholder declaration) both have non-Claude-only fixture coverage.
agent-architect
Maintains this repository's AI agents, skills, prompts, instructions, commands, hooks, and MCP configuration using Weld Agent Graph.
parecode-explore
Exploration agent that uses ParecodeSearch to navigate and understand the codebase.
planner
Drafts implementation plans for Claude Code.
reviewer
Reviews dependency security risk.