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/james-prodopen/emcmdWrote 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/commands/james-prodopen/emcmd/jira-duplicate-bugs)<a href="https://agentmods.dev/commands/james-prodopen/emcmd/jira-duplicate-bugs"><img src="https://agentmods.dev/badge/commands/james-prodopen/emcmd/jira-duplicate-bugs/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/commands/james-prodopen/emcmd/jira-duplicate-bugs"><img src="https://agentmods.dev/badge/commands/james-prodopen/emcmd/jira-duplicate-bugs.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 | $0.00000 | $0.00747 |
| Opus 5.5 | $0.00000 | $0.00299 |
| Sonnet 5.5 | $0.00000 | $0.00149 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
jira-duplicate-bugs 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 2mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find potential duplicate bugs in a Jira project. Provide PROJECT_KEY here: $ARGUMENTS.
Workflow
Follow these instructions explicitly:
- Use
acli jira auth statusto get the "Site" value, which will be used to generate URLs later - Use
acli jira workitem search --json --jql "project={PROJECT_KEY} and issuetype=Bug" --paginateto fetch all work items in the project, iterating through all pages if need be - Output a working table of unique work item pairs, where at least one work item in the pair does not have status.name of "Done" - for example, assuming you have work items A and B
- if (A status.name != "Done" AND B status.name != "Done") OR (A status.name = "Done" AND B status.name != "Done") OR (A status.name != "Done" AND B status.name = "Done") include a row (A,B) in the table
- do not create a duplicative row (B,A) in addition to (A,B)
- table schema should be (A.key | A.summary | B.key | B.summary)
- DO NOT truncate summary text
- Did you output a working table in step 3? If not, go back to step 3 and output a working table - DO NOT proceed unless that has been completed
- Analyze all work item PAIRS in the previously created working table to identify potential duplicates based on similar summary text
- when analyzing, consider only a single row at a time to avoid finding work item pairs that both have status.name = "Done"
- For each potential duplicate pair, use
acli jira workitem link list --key "{key}" --jsonon BOTH of the work items to check if they are already linked to each other- you need to check both work items because that acli command supports "duplicates" but not "is duplicated by" relationships
- If the pair of work items is not already linked, use
acli jira workitem view "{key}" --fields "issuetype,summary,description"for both work items to review them in additional detail and increase confidence that they are duplicates - For each pair of work items that are duplicates, generate URLs for each work item using the format:
https://{site}/browse/{key}
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.
- 2mo ago First seen · 42 lines · 0 tokens per session scan A 11b96555be95
jira-duplicate-bugs is a command published in the GitHub repository james-prodopen/emcmd (5 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 747 tokens. 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 2026-08-31.
Other commands, from other repositories
bug-report
Draft a bug report issue for lean4-skills.
triage
Query open Node bugs, classify by priority and sub-team, suggest assignments, and generate a triage summary.
speckit.companion.doctor
Report on a spec's run health — unfinished steps, unjournaled tasks, step bleed, drift you can judge, a step that closed having verified nothing, a step that closed without the file it promised, and why completion did not land (read-only, retroactive, never halts).
postmortem
Deliver a structured post-mortem after incidents, mistakes, or stuck sessions. Use when the user requests a structured post-mortem after incidents, mistakes, or stuck sessions.
audit
Audit closed tickets for regressions against today's code (unchanged, evolved, implemented wrong, not implemented), plus duplicate and groupable open ones.
harness:maintenance-pipeline
On-demand, report-first maintenance sweep — runs overdue checks via harness maintenance run, triages findings, and asks the human in plain text before dispatching any fix.