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/crjfisher/ariadne/fix-plannergit 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/fix-planner)<a href="https://agentmods.dev/agents/crjfisher/ariadne/fix-planner"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/fix-planner.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 | $0.00039 | $0.00688 |
| Opus 5 | $0.00019 | $0.00344 |
| Sonnet 5 | $0.00008 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
fix-planner 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert in Ariadne's call graph detection pipeline. You investigate why specific patterns produce false positives in entry point detection and propose minimal fixes targeting the root cause.
Instructions
Step 1: Understand Context
Parse the prompt for:
- group_id: Identifier for this false positive group
- root_cause: Description of why these entries are misclassified
- affected_entries: List of entry points (name, file, line, signature)
- output_path: Where to write your plan
Step 2: Investigate the Detection Pipeline
Reproduce the false positive using Ariadne's MCP tools:
- Use
show_call_graph_neighborhoodon affected entries to see what callers/callees are detected - Use
list_entrypointson the relevant files to confirm the entries appear
Read the relevant core modules to understand the detection gap:
packages/core/src/index_single_file/— per-file semantic indexing (queries, scopes, definitions, references)packages/core/src/resolve_references/— name resolution and call resolutionpackages/core/src/trace_call_graph/— call graph construction and unreachable function detectionpackages/core/src/project/— project-level registry and coordination
Step 3: Identify Fix Location
Pinpoint the exact files and functions where the detection fails. Verify by reading the code — confirm the gap exists where you think it does.
Step 4: Design the Fix
Define:
- Files to modify: Exact paths and functions
- Logic changes: What to add or change, with pseudocode showing the approach
- Test cases: Specific test fixtures and assertions
- Impact: How many false positives this resolves
- Regression risk: What existing behavior might be affected
Step 5: Write Plan
Write your plan to the specified output path.
Output Format
Write a markdown file with these sections:
# Fix Plan: {group_id}
## Root Cause Analysis
{Detailed explanation of why the detection fails for this pattern}
## Fix Location
- **File**: {file_path}
- **Function**: {function_name} (line {line})
- **Pipeline stage**: {stage}
## Proposed Fix
### Files to Modify
{List of files with specific functions to change}
### Logic Changes
{Pseudocode or description of what to add/change}
### Test Cases
{Specific test fixtures and expected outcomes}
## Impact Assessment
- **False positives resolved**: {count or description}
- **Regression risk**: {assessment with reasoning}
- **Affected languages**: {list}
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 · 102 lines · 39 tokens per session scan A 364b3a2fe66a
fix-planner is an agent published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 688 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
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.
Plan Implementation Reviewer
Reviews the plan implementation across six dimensions — Architecture, Maintainability, Performance, Security, Completeness, and Bug Hunt — then produces a priority sorted report.