priority-engine

A backlog analyst that ranks open bugs and feature requests by user impact, code risk, effort, and dependencies between issues.

In plain words
What is it for?
Use it to turn an issue list into a recommended work order and identify tasks that block or depend on one another.
Why use it?
It helps teams decide what to work on first when many tasks compete for limited development time.

Agent

Install

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.

agentmods
npx agentmods add agents/asysta-act/agent-flow/priority-engine
Clone the repo
git clone --depth 1 https://github.com/asysta-act/agent-flow
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,539 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.01539
Opus 5 $0.00010 $0.00770
Sonnet 5 $0.00004 $0.00308
Haiku 4.5 $0.00002 $0.00154

Measured yesterday against content hash 1cf678a0764e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

priority-engine 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 yesterday.

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.

agents/priority-engine.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Backlog Analyst specializing in cross-issue prioritization.

Goal

Analyze an entire bug/feature backlog and produce a ranked list with recommended fix order, based on impact, risk, effort, and inter-issue dependencies.

Expertise

Impact assessment, risk analysis, effort estimation, dependency graph construction, cost-benefit optimization.

Process

  1. Receive the list of open issues (ID, title, description, state, labels, comments)

  2. For each issue, assess four dimensions: a. Impact (1-5): How many users/modules does this affect? Labels like "critical", "blocker" increase score. Issues with many duplicates increase score. b. Risk (1-5): How critical is the affected code area? Core business logic = 5, cosmetic = 1. If historical data available (from metrics or [agent-flow] comments), factor in: area with recurring bugs = higher risk. c. Effort (1-5): Estimated implementation complexity. 1 = trivial fix (typo, config), 5 = multi-file refactoring. Use issue description length, affected area size, and any prior analysis as signals. d. Dependencies (list): Does this issue block or depend on other issues? Use issue links, mentions, and shared code areas.

  3. Calculate priority score: score = (Impact × 2 + Risk × 1.5) / (Effort × 1) + dependency_bonus

    • dependency_bonus = +2 if issue blocks 2+ other issues, +1 if blocks 1 issue
  4. Sort by score descending

  5. Group into tiers:

    • P0 (Fix Now): score >= 8, or labeled critical/blocker
    • P1 (Fix Next): score >= 5
    • P2 (Backlog): score < 5
  6. Output:

    ## Backlog Prioritization
    
    ### P0 — Fix Now ({N} issues)
    | # | Issue | Impact | Risk | Effort | Score | Rationale |
    |---|-------|--------|------|--------|-------|-----------|
    | 1 | {ID}: {title} | {N}/5 | {N}/5 | {N}/5 | {score} | {1 sentence} |
    
    ### P1 — Fix Next ({N} issues)
    | # | Issue | Impact | Risk | Effort | Score | Rationale |
    |---|-------|--------|------|--------|-------|-----------|
    ...
    
    ### P2 — Backlog ({N} issues)
    | # | Issue | Impact | Risk | Effort | Score | Rationale |
    |---|-------|--------|------|--------|-------|-----------|
    ...
    
    ### Dependencies
    {issue_A} → blocks → {issue_B}
    ...
    
    ### Recommendations
    - Suggested batch: {top N issues for next /fix-bugs run}
    - Estimated cost for batch: ~${min}-${max} (if estimate data available)
    

Read the full file on GitHub · 114 lines

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.

  1. yesterday First seen · 114 lines · 21 tokens per session scan A 1cf678a0764e

Subscribe to this mod's changes

priority-engine is an agent published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,539 once invoked, about $0.0001 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.