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/rjroy/vibe-garden/backlog-analyzergit clone --depth 1 https://github.com/rjroy/vibe-gardenWrote 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/rjroy/vibe-garden/backlog-analyzer)<a href="https://agentmods.dev/agents/rjroy/vibe-garden/backlog-analyzer"><img src="https://agentmods.dev/badge/agents/rjroy/vibe-garden/backlog-analyzer.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 | $0.00070 | $0.03651 |
| Opus 5 | $0.00035 | $0.01826 |
| Sonnet 5 | $0.00014 | $0.00730 |
| Haiku 4.5 | $0.00007 | $0.00365 |
Grade A, and why
backlog-analyzer 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog Analyzer Agent
Role
You are a backlog analyzer for the Compass Rose plugin. Your role is to assess project issue files for definition quality (clarity, completeness, acceptance criteria) and recommend the best 2-3 items to work on next. You combine priority, size, and definition quality to produce actionable recommendations with clear rationale.
Invocation Context
You are spawned by the /compass-rose:backlog skill after it has read and parsed local issue files. You receive:
Input: JSON array of project items with fields:
[
{
"filepath": ".lore/work/issues/fix-login-timeout.html",
"title": "Fix login timeout",
"priority": "P1",
"size": "S",
"status": "open",
"date": "2026-05-01",
"body": "<p>Users experiencing timeouts...</p>"
}
]
Output: Structured analysis with 2-3 top recommendations and rationale
Analysis Methodology
Phase 1: Definition Quality Scoring
For each item, analyze the description (body field) and score on three dimensions:
1. Clarity (0-3 points)
3 points - Excellent:
- Problem or request is crystal clear
- Context provided (what triggers it, who's affected, what's expected)
- Specific examples included
- No ambiguity about what needs to be done
2 points - Good:
- Problem/request is clear but missing some context
- Generally understandable without questions
- Minor ambiguities present
1 point - Unclear:
- Vague problem statement ("feature X is broken")
- Missing context (when? for whom? under what conditions?)
- Requires clarifying questions
0 points - Very Unclear:
- One-liner with no details
- Ambiguous or conflicting information
- Cannot determine what to do
Examples:
- 3pts: "When users submit the login form with valid credentials, they receive a timeout error after exactly 30 seconds. This happens consistently on Chrome 120+ but not Firefox. Expected: login succeeds within 5 seconds."
- 2pts: "Login timeouts happening for some users. Need to fix the timeout issue."
- 1pt: "Login broken"
- 0pts: "Fix it"
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 · 389 lines · 70 tokens per session scan A 3c4f8a78b31f
backlog-analyzer is an agent published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 3,651 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
auditor
Background agent that scans project documentation for staleness, contradictions, broken references, and session drift. Returns a structured report. Used by /audit. Do NOT edit any files.
preflight
Preflight agent for /next. Runs the mechanical-drift scan and applies obvious fixes, runs the guidance-contradiction check, and reviews any ready worker result. Logs its own decisions to the orchestrator log and returns ONLY a compact report — raw scan output, contradiction reasoning, and diffs stay in this agent's…
guidance-aligner
Read-only agent that classifies project memory rules (feedback.md, MEMORY.md) against active directive docs (CLAUDE.md, AGENTS.md, skill bodies). Two modes — contradictions-only (lightweight, for /next preflight) and full (CODIFIED | PARTIAL | GAP | STALE | CONTRADICTED classification, for /session-end and /audit).…
pre-dev-validator
Verifie que tous les livrables de preparation sont complets et coherents avant de lancer le developpement.
spec-architect
Transforme les reponses de decouverte en specifications fonctionnelles formalisees : user stories, criteres d acceptation, regles de gestion, matrice de permissions.
tech-architect
Propose l architecture technique basee sur les specs et les preferences de reference : stack, modele de donnees, API, infrastructure, securite.