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/koolamusic/claudefiles/jira-advisorgit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/koolamusic/claudefiles/jira-advisor)<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>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 | $0.00043 | $0.00636 |
| Opus 5 | $0.00022 | $0.00318 |
| Sonnet 5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
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.
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:
- Advisory type —
triageorplan - Sprint slug (if applicable)
- Artifacts to review — paths to all relevant files
- 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.
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 · 68 lines · 43 tokens per session scan A 1b269ba98d20
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.