advisor

advisor is a command for coding agents from koolamusic/claudefiles. It costs 41 tokens per session (940 once invoked), scanned A, original, MIT.

A second-opinion review step for triage and planning decisions. Triage means deciding how an issue should be handled, while a plan describes the work and its order.

In plain words
What is it for?
Use it to review issue labels and next steps, or to assess sprint plans, task breakdowns, and risk coverage.
Why use it?
It challenges the first proposal, exposing assumptions, risks, and possible alternatives before the team commits.

Command

Part of the jira plugin — 13 commands, 9 agents shipped together

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 commands/koolamusic/claudefiles/advisor
Clone the repo
git clone --depth 1 https://github.com/koolamusic/claudefiles

Or install jira, the plugin that ships this one along with the rest of its 13 commands, 9 agents.

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.

agentmods badge for advisor

README.md
[![agentmods](https://agentmods.dev/badge/commands/koolamusic/claudefiles/advisor.svg)](https://agentmods.dev/commands/koolamusic/claudefiles/advisor)
Your own site
<a href="https://agentmods.dev/commands/koolamusic/claudefiles/advisor"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 940 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 $0.00041 $0.00940
Opus 5 $0.00020 $0.00470
Sonnet 5 $0.00008 $0.00188
Haiku 4.5 $0.00004 $0.00094

Measured 3d ago against content hash 52fa214bb1de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advisor 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 3d 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.

plugins/jira/commands/advisor.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Get a second opinion before committing to a triage decision or plan. The advisor is an independent agent that reads the same artifacts but approaches them from a skeptical stance.

Parse the input

$ARGUMENTS:

  • triage — advise on a triage recommendation (issue labels, state transition, agent brief)
  • plan — advise on sprint plans (wave structure, task decomposition, risk coverage)
  • --sprint <slug> — target a specific sprint (default: active)

If empty, infer from sprint state:

  • If plans exist but no EXECUTION.md: assume plan
  • If no plans: assume triage
  • If ambiguous: ask

Context gathering

For triage advisory

Read:

  • The issue under triage (from gh issue view or the sprint's BRIEF.md)
  • Any existing triage notes or comments
  • .jira/STATE.md — prior sprint patterns and decisions log
  • .project/PROJECT.md — project-level goals (does this issue align?)
  • .project/ROADMAP.md — is this the right time for this work?

For plan advisory

Read:

  • All *-PLAN.md files in the sprint
  • CONTEXT.md — locked decisions
  • RESEARCH.md — original research findings
  • BRIEF.md — the original problem statement

Spawn the advisor agent

Single Agent call with the jira-advisor agent:

You are the advisor — an independent reviewer challenging the current <triage|plan> recommendation.

## Your inputs
<all gathered context>

## Your job
Produce a structured advisory with three sections:

1. **Challenges** — assumptions in the <recommendation|plan> that might be wrong. For each:
   - What's assumed
   - Why it might not hold
   - What breaks if it doesn't
   - Severity: BLOCKER / RISK / MINOR

2. **Alternatives** — different approaches the <triage|planner> didn't consider. For each:
   - What it is
   - What it costs vs the current approach
   - When you'd pick it over the current approach

3. **Endorsements** — parts of the <recommendation|plan> that are solid. Don't manufacture criticism for things that hold up.

## Rules
- Be specific. "This might not scale" is noise. "The N+1 query on line 45 of 02-PLAN.md will timeout with >1000 entries because..." is signal.
- Reference artifacts by path and section.
- Don't rewrite the plan. Challenge it.
- If everything looks solid, say so in 3 lines. Don't pad.

Read the full file on GitHub · 100 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. 3d ago First seen · 100 lines · 41 tokens per session scan A 52fa214bb1de

Subscribe to this mod's changes

advisor is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 940 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.