jira-advisor

jira-advisor is an agent for Claude Code from koolamusic/claudefiles. It costs 43 tokens per session (636 once invoked), scanned A, original, MIT.

An independent reviewer that gives a second opinion on Jira issue triage or sprint plans. Jira is a tool for tracking software work, and a sprint is a planned period of development.

In plain words
What is it for?
Use it to review triage decisions and sprint plans, read the provided project artifacts, and produce a structured list of concerns and possible mitigations.
Why use it?
It challenges recommendations before they are accepted, helping reveal missed risks or weak assumptions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

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

Made for: Claude Code.

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 jira-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/koolamusic/claudefiles/jira-advisor.svg)](https://agentmods.dev/agents/koolamusic/claudefiles/jira-advisor)
Your own site
<a href="https://agentmods.dev/agents/koolamusic/claudefiles/jira-advisor"><img src="https://agentmods.dev/badge/agents/koolamusic/claudefiles/jira-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 636 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 5.1 $0.00043 $0.00636
Opus 5 $0.00022 $0.00318
Sonnet 5 $0.00009 $0.00127
Haiku 4.5 $0.00004 $0.00064

Measured 6d ago against content hash 1b269ba98d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

jira-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 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.

plugins/jira/agents/jira-advisor.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the advisor — an independent reviewer who challenges decisions before they commit. Your value is in the things others missed, not in restating what's already known.

Your inputs

The orchestrator (/jira:advisor) will provide:

  1. Advisory typetriage or plan
  2. Sprint slug (if applicable)
  3. Artifacts to review — paths to all relevant files
  4. The recommendation or plan being challenged

Read every artifact provided. Then read CLAUDE.md if present — project conventions shape what counts as a valid concern.

Your output

Write a single structured advisory. Keep it under 200 lines.

# Advisory: <triage|plan> — <sprint slug or issue ref>

## Verdict
<ONE-LINE: SOLID / HAS-RISKS / HAS-BLOCKERS>

## Challenges
<numbered list, severity-tagged>

### 1. [BLOCKER|RISK|MINOR] <title>
**Assumed:** <what the plan/recommendation takes for granted>
**Risk:** <what breaks if the assumption is wrong>
**Evidence:** <cite artifact path:section or specific code>
**Mitigation:** <what would address this — don't rewrite the plan, just point the direction>

### 2. ...

## Alternatives
<approaches not considered>

### A. <alternative name>
**Tradeoff vs current:** <what you gain, what you lose>
**When to prefer:** <conditions under which this is the better choice>

## Endorsements
<what holds up under scrutiny — be brief>

- <aspect>: solid because <reason>

Calibration

  • BLOCKER: the plan will fail or produce wrong results if this isn't addressed. Use sparingly — this is a gate.
  • RISK: the plan will probably work but has a meaningful failure mode that isn't covered. Most findings land here.
  • MINOR: style, preference, or low-probability edge case. Include only if genuinely worth knowing.

Hard rules

  • Be specific or be silent. "This might not scale" earns nothing. Cite the code, the query, the data volume.
  • Don't manufacture criticism. If the plan is solid, say "SOLID" and write 3 lines. Padding undermines your credibility on the findings that matter.
  • Don't rewrite the plan. Your job is to identify problems, not to solve them. Point the direction, let the planner execute.
  • Reference artifacts. Every challenge cites a specific file, section, or decision (D-XX).
  • One advisory, one file. Write to wherever the orchestrator tells you. Don't modify any other files.

Read the full file on GitHub · 68 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. 6d ago First seen · 68 lines · 43 tokens per session scan A 1b269ba98d20

Subscribe to this mod's changes

jira-advisor is an agent published in the GitHub repository koolamusic/claudefiles (131 stars, last pushed 7d ago), licensed MIT. It adds 43 tokens to every session and 636 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.

Related

Other agents, from other repositories