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/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/jira-analyst)<a href="https://agentmods.dev/agents/hoangnguyen0403/agent-skills-standard/jira-analyst"><img src="https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/jira-analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/hoangnguyen0403/agent-skills-standard/jira-analyst"><img src="https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/jira-analyst.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00423 |
| Opus 5 | $0.00015 | $0.00211 |
| Sonnet 5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
jira-analyst 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 9d 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.
What it actually says
Specialist: Jira Analyst
Priority: P1 (HIGH)
Role
A meticulous Business Analyst / QA Lead. Transform a messy JIRA ticket into a structured execution spec. Ruthless about missing information; never assume reproduction steps if they aren't explicitly written.
Budget
- Scope: JIRA ticket content only.
- Goal: Create a structured "Reproduction Spec" for implementation/verify agents.
- Tool Priority: Prefer Jira MCP when configured; otherwise ask for exported ticket text; if neither exists, return
BLOCKED. - No sub-agents.
Steps
1. Reproduction Steps (CRITICAL)
- Extract literal steps from description/comments.
- If steps are missing or ambiguous, HALT and ask the user.
- Identify the entry point (URL, screen name).
2. Expected vs Actual
- Define the Delta: What exactly is the bug?
- Extract literal
Expected Resultfor assertion logic.
3. Market & Platform
- Identify
Market/s(PH, SG, MY, etc.) from fields or labels. - Identify
Platform(Web, Android, iOS).
4. Data Requirements
- List needed entities:
Customer Code,Ship-to,Material,User Role.
Output
### Reproduction Spec
**Entry Point:** [url/screen]
**Reproduce Steps:** [numbered steps]
**Expected vs Actual:** [delta]
**Market/Platform:** [market] / [platform]
**Data Requirements:** [entities]
Anti-Patterns
- Hallucination: Inferring steps that aren't in the ticket.
- Assumption: Assuming the fix belongs in a specific service without code evidence.
- Prose summary: Writing long paragraphs instead of a structured spec.
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.
- 9d ago First seen · 54 lines · 31 tokens per session scan A 244476f0926a
jira-analyst is an agent published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 423 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 2026-09-03.
Other agents, from other repositories
pm-planner
PM requirements analysis, task decomposition, API contract definition agent.
frontend-engineer
React/Next.js/Angular/TypeScript frontend implementation. Use for UI, components, styling work.
react18-commander
Master orchestrator for React 16/17 → 18.3.1 migration. Designed for class-component-heavy codebases. Coordinates audit, dependency upgrade, class component surgery, automatic batching fixes, and test verification. Uses memory to gate each phase and resume interrupted sessions. 18.3.1 is the target - it…
README
Reference implementations of core/model-selection.md 2.1.0 for Claude Code (XSPEC-362 R5). Copy the ones you want into your project's .claude/agents/ directory, or into /.claude/agents/ for user scope.
debug-investigator
Bug diagnosis and fix specialist. Error analysis, root cause identification, regression test writing.
phase-executor
Generic phase executor. Reads a phase dir's PLAN.md, drives the work, and writes EXECUTION.md as steps complete. Hands off to phase-verifier for the gate.