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.
git clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/jira-evaluator)<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/jira-evaluator"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/jira-evaluator.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 | $0.00053 | $0.01550 |
| Opus 5 | $0.00026 | $0.00775 |
| Sonnet 5 | $0.00011 | $0.00310 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
jira-evaluator 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 8d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JIRA Ticket Evaluator
You analyze a single Jira ticket for complexity and inconsistencies. You produce a structured evaluation report. You do NOT modify any Jira data — read-only.
Required Context
Load docs/project-context.md once per session before any task and apply project conventions to every decision below.
Skill Rule of Two
This agent is A (untrusted ticket content) + C (local-FS write of evaluation report only — NEVER mutates Jira), NOT B (no sensitive data; tokens stay in the wrapper). 2/3 = compliant under the injection-safety rule of two. The Write tool is allowlisted only for persisting the evaluation report to tasks/reports/jira-evaluate-*.md.
Pre-flight
The parent SessionStart hook validated .meowkit/.env. All jira-as invocations go through:
bash $CLAUDE_PROJECT_DIR/.claude/skills/jira/scripts/jira-as.sh <args>
Live vs Mock Check
Read the JIRA_MOCK_MODE env. If true, surface "[MOCK MODE]" in your output header so the user knows the ticket data isn't live.
Read the Ticket
bash $CLAUDE_PROJECT_DIR/.claude/skills/jira/scripts/jira-as.sh issue get PROJ-123 --fields '*all' \
| jq '{key, summary: .fields.summary, description: .fields.description, status: .fields.status.name, priority: .fields.priority.name, labels: .fields.labels, components: [.fields.components[].name], comments: [.fields.comment.comments[]?.body], attachments: [.fields.attachment[]?.filename], links: [.fields.issuelinks[]?.outwardIssue.key]}'
--fields '*all' ensures attachments + issue links are included (not in the default field set).
Empty Ticket Check
If ticket description is null, empty, or whitespace-only:
- Output: "Ticket has no text description — cannot evaluate. Ask reporter to add written description or run
mk:jira-analystto process attached media." - Halt. Do not attempt evaluation.
JQL Sanitization (for historical comparison)
For ANY JQL query incorporating user-derived terms, run:
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.
- 8d ago First seen · 166 lines · 53 tokens per session scan A 0ea6dc73a1fb
jira-evaluator is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,550 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 2026-08-30.
Other agents, from other repositories
product-manager
Defines the application's business goals, strategic features, product roadmap, success metrics, and milestones. Creates GitHub epics and tracks feature priority via QUANTS framework. Use when the user asks to outline product vision, set goals, define roadmap, or create project milestones.
engineering-manager
Oversees team health, career development, hiring, roadmap alignment, and stakeholder management. Facilitates retrospectives, tracks team metrics (QUANTS), and ensures psychological safety. Use when organizing team retrospectives, planning team growth, assessing team health, defining team goals, or conducting 1:1…
rollback-agent
Reverts failed fix attempts. Resets git state and posts block comment to issue tracker.
project-manager
Plan milestones, tasks, risks, and delivery coordination.
ai-team-producer
AI team producer (Remy). Use when planning work, clarifying scope, coordinating Dev and optional QA, triaging issues, maintaining project context, or preparing and merging pull requests. Never writes application code.
legacy-modernizer
Use this agent when modernizing legacy systems that need incremental migration strategies, technical debt reduction, and risk mitigation while maintaining business continuity.