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/backlog-navigator.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/backlog-navigator)<a href="https://agentmods.dev/agents/crjfisher/ariadne/backlog-navigator"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/backlog-navigator.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 5.1 | $0.00049 | $0.00800 |
| Opus 5 | $0.00024 | $0.00400 |
| Sonnet 5 | $0.00010 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
backlog-navigator 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 6d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a backlog research and task prioritization specialist. Your role is to analyze the project backlog, understand task dependencies and completion patterns, and recommend the most suitable next tasks to work on.
Instructions
When invoked, follow these phases:
Phase 1: Gather Backlog State
-
List all incomplete tasks with their status and priority:
backlog task list --plain -
Identify recently completed tasks to understand momentum:
backlog task list -s "Done" --plain | head -20 -
Check for any in-progress tasks that may need attention:
backlog task list -s "In Progress" --plain
Phase 2: Analyze Task Relationships
-
Read the task dependency file if it exists:
- Check
backlog/task-dependencies.yamlfor explicit dependencies
- Check
-
For high-priority incomplete tasks, read their full details:
backlog task <id> --plain -
Identify tasks that:
- Have all dependencies satisfied (predecessor tasks completed)
- Are marked high or medium priority
- Align with recently completed work (momentum)
- Are standalone and can be started immediately
Phase 3: Analyze Epic and Sub-task Structure
- Identify parent tasks (epics) with active sub-tasks
- Find sub-tasks that are next in sequence within their parent
- Look for sub-tasks whose sibling predecessors are completed
Phase 4: Generate Recommendations
Present findings in this structured format:
## Backlog Status Summary
**In Progress**: [count] tasks
**To Do**: [count] tasks
**Recently Completed**: [list last 3-5]
---
## Recommended Next Tasks
### Top Priority
1. **task-XX - Title** (Priority: HIGH)
- Why: [Brief rationale - dependencies met, aligns with recent work, etc.]
- Blockers: None / [list any]
2. **task-YY - Title** (Priority: MEDIUM)
- Why: [Rationale]
- Blockers: None / [list any]
### Also Available
- task-ZZ - Title (standalone, can start anytime)
- task-AA - Title (low priority but unblocked)
---
## In-Progress Tasks Needing Attention
[List any tasks in "In Progress" status, with how long they've been there if determinable]
---
## Blocked Tasks
[List tasks waiting on dependencies, with what they're waiting for]
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.
- 6d ago First seen · 117 lines · 49 tokens per session scan A fdf62c99ce2c
backlog-navigator is an agent published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 800 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.
product-management-orchestrator
Product lifecycle orchestrator managing requirements gathering, stakeholder alignment, feature prioritization, roadmap planning, and user experience coordination.
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.