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 skills add monkilabs/opencastle --skill jira-managementgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/skills/monkilabs/opencastle/jira-management)<a href="https://agentmods.dev/skills/monkilabs/opencastle/jira-management"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/jira-management/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/skills/monkilabs/opencastle/jira-management"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/jira-management.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 | $0.00041 | $0.00505 |
| Opus 5.5 | $0.00016 | $0.00202 |
| Sonnet 5.5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
jira-management 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 11d 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
Task Management with Jira
Project keys, workflow state IDs, and board config: .opencastle/project/jira-config.md. Docs: https://developer.atlassian.com/cloud/jira/platform/
Gotchas
- Transitions are constrained by the project's workflow — a jump the board does not allow fails even with a valid status name. Read the workflow state IDs from
jira-config.mdbefore transitioning; retry once, then stop. - Status names in JQL must be quoted when they contain spaces:
status = "In Progress". - A
createcall is only successful if it returns an issue key. Verify before treating the issue as tracked. - PR-driven status updates only happen when the GitHub/Jira integration is configured; link by putting the key (
PROJ-123) in the branch or PR title.
Conventions
Summary format [Area] Short description — e.g. [Schema] Add priceRange field, [DB] Add price_range column, [UI] Build PriceRangeFilter, [Test] E2E price range filtering.
Every description must carry: Objective (one sentence), Files (partition) (paths this agent may modify), Acceptance Criteria (verifiable checklist), Dependencies (issue keys). Group under an Epic; use components or labels for domain grouping.
Flow Backlog → To Do → In Progress → In Review → Done. Agent moves To Do → In Progress on start, In Progress → Done only after verification.
Untracked bug found mid-task: search Jira first; if absent create a [Bug] in Backlog with symptoms, repro steps, and affected files.
JQL
project = PROJ AND status = "In Progress" ORDER BY priority DESC
project = PROJ AND type = Bug AND status != Done ORDER BY priority DESC
project = PROJ AND sprint in openSprints() ORDER BY priority DESC
project = PROJ AND priority = Highest AND status != Done
Session: query in-progress work first → decompose into issues → link dependencies → transition before/after each → on completion verify all Epic issues Done, run build/lint/test, close the Epic.
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.
- 11d ago Changed · -2 lines · -12 tokens per session c80365844849
- 12d ago First seen · 39 lines · 53 tokens per session scan A 37d25c362850
jira-management is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 505 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
jira-ticket-builder
Turns rough input into structured Jira work. Two modes — single-ticket mode turns a bug description, meeting notes, Slack thread, incident writeup, or a few sentences into one fully-structured Jira ticket; decomposition mode turns a rough requirements doc or product brief with multiple asks and open questions into…
task-forest
Maintains a repo-local task forest or task DAG for the current workspace. Use when the user asks to initialize or update a task forest, close a session, summarize evolving project work, align a request with a global goal, track progress/history/deviations/todos, save or apply a task proposal, or export the…
work-report-expert
A writing guide for workplace summaries and presentations, including annual reviews, performance reports, project updates, job-promotion speeches, weekly reports, and monthly reports. It uses clear conclusions, evidence, and the STAR method, which explains a Situation, Task, Action, and Result.
workflow-discovery
Rank workflow candidates using observed repositories, skills, engineering activity and recurring user requests.
product-architect
Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…
using-todo
Use when an Agent needs to capture, find, update, finish, cancel, or reopen durable deferred work in LWC.