A headless pipeline stage that finds possible entry points—places where a program can start—in Ariadne packages or other codebases, then checks which findings are false positives.

Use it to scan a codebase, investigate entry-point candidates, reuse confirmed results where appropriate, and publish a self-contained triage run.

It avoids treating every detected entry point as real and records the evidence and cause for each false positive.

How CRJFisher/ariadne configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/CRJFisher/ariadne/main/.claude/skills/triage/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/CRJFisher/ariadne

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/crjfisher/ariadne/triage/github.svg)](https://agentmods.dev/skills/crjfisher/ariadne/triage)

Your own site

<a href="https://agentmods.dev/skills/crjfisher/ariadne/triage"><img src="https://agentmods.dev/badge/skills/crjfisher/ariadne/triage/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/crjfisher/ariadne/triage"><img src="https://agentmods.dev/badge/skills/crjfisher/ariadne/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,678 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00042	$0.08678
Opus 5.5	$0.00017	$0.03471
Sonnet 5.5	$0.00008	$0.01736
Haiku 4.5	$0.00004	$0.00868

Measured 5d ago against content hash c514ee53a71f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

triage scanned grade C with 1 finding 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.

The scan reads SKILL.md. This mod also ships 50 executable files (scripts/abandon_run.ts, scripts/build_transfer_manifest.test.ts, scripts/build_transfer_manifest.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| `analysis_output/<project>/triage_results/` | **Preserve** | Never `rm -rf`. These finalized triage-results JSON files are the permanent source of truth for the TP cache (read by `confirmed_unreachable_reuse.derive_tp_

.claude/skills/triage/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Entrypoints

Triage pipeline for entry point analysis: detect false positives and classify root causes. Supports both self-analysis (Ariadne packages) and external codebase analysis.

This pipeline runs headlessly, end to end, in a single turn. Every phase — config creation, file-count checks, dispensing, investigating, finalizing — proceeds on sensible defaults without pausing for confirmation. Never call AskUserQuestion anywhere in this skill; it is not in this skill's allowed-tools. When a step below says "ask" or "confirm," that describes an interactive fallback this skill does not use — resolve it autonomously instead, per the guidance at that step, and log the decision in your reply text rather than pausing for input.

Each invocation produces a self-contained run under triage_state/<project>/runs/<run-id>/. Run-id format is <short-commit>-<iso-ts> (e.g. deadbee-2026-04-28T13-42-07.812Z); nogit-... for non-git projects. Re-running at the same target commit reuses prior confirmed_unreachable verdicts via the TP cache (skip with --no-reuse-tp). Moving the target to a new commit (--commit <sha>, see Phase 1) busts the cache: every entry re-investigates.

Script invocation: Always use node --import tsx to run the TypeScript scripts. Never use pnpm exec tsx or npx tsx — these create IPC Unix sockets that the sandbox blocks.

Pipeline Overview

Phase	Script / Agent	Purpose
0. Environment	`scripts/ensure_environment.sh`	Install dependencies and build the workspace packages the scripts import, where needed
1. Detect	`scripts/detect_entrypoints.ts`	Run entry point detection
2. Prepare	`scripts/prepare_triage.ts`	Classify against the known-issues registry via `enrich_call_graph`, build triage state
3. Triage Loop	triage-investigator	Investigate residual entries; each writes one self-contained verdict to `results/`
4. Finalize	`scripts/finalize_triage.ts`	Publish the v5 triage-results JSON built entirely from the per-entry verdict files

Read the full file on GitHub · 411 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 Changed · +13 lines c514ee53a71f
17d ago First seen · 398 lines · 42 tokens per session scan C 5f8d8d2eef60

Subscribe to this mod's changes

triage is a skill published in the GitHub repository CRJFisher/ariadne (23 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 8,678 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.

Debugging TypeScript ast code-intelligence nodejs parser tree-sitter

migrate-oxlint

Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.

oxc-project/oxc · 44 tokens

tree-sitter-language-pack-extracting-code-structure

Use when the user wants structured code metadata from a source file — functions, classes, imports, exports, symbols, docstrings, comments, or syntax diagnostics. Covers ts-pack process feature flags, the JSON result shape, and the default feature set.

xberg-io/tree-sitter-language-pack · 52 tokens

tree-sitter-language-pack-parsing-source

Use when the user wants a tree-sitter syntax tree for a source file — an s-expression dump or JSON tree. Covers ts-pack parse, language auto-detection vs --language, stdin input, and reading haserrors.

xberg-io/tree-sitter-language-pack · 48 tokens

webiny-api-logger-catalog

Name: Logger Import: import { Logger } from "webiny/api/logger" Source: @webiny/api-core/features/logger/index.ts Description: Structured logging with multiple log levels.

webiny/webiny-js · 16 tokens

detect-ssr-leak

Detect server-side memory leaks in Node.js SSR services. Use when user asks to "check for memory leak", "detect leak", "SSR memory leak", "memory leak", or wants to diagnose growing memory usage on a Node.js server. TRIGGER when user mentions memory leak detection, especially for SSR/Vue/React server-side rendering.

cabloy/cabloy · 75 tokens

frigg-first-code-search

Default to Frigg MCP instead of shell rg/grep/find/fd/cat/sed for source-code discovery, search, navigation, and proof reads in attached repos. Scenario-first routing: pick the flow, then the tool. Shell remains correct for git, build/test output, generated/unindexed paths, explicit live-disk checks, and when Frigg is…

bnomei/frigg · 80 tokens

ariadne: Skill for Claude Code