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 commands/sablier-labs/plugin-marketplace/create-issuegit clone --depth 1 https://github.com/sablier-labs/plugin-marketplaceWrote 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/sablier-labs/plugin-marketplace/create-issue)<a href="https://agentmods.dev/commands/sablier-labs/plugin-marketplace/create-issue"><img src="https://agentmods.dev/badge/commands/sablier-labs/plugin-marketplace/create-issue.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 | $0.00012 | $0.01518 |
| Opus 5 | $0.00006 | $0.00759 |
| Sonnet 5 | $0.00002 | $0.00304 |
| Haiku 4.5 | $0.00001 | $0.00152 |
Grade A, and why
create-issue 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 4d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- GitHub CLI auth: !
gh auth status 2>&1 | rg -q "Logged in" && echo "authenticated" || echo "not authenticated" - Arguments: $ARGUMENTS
Skills
Activate the gh-cli skill for this command.
Your Task
STEP 1: Validate prerequisites
IF not authenticated: ERROR "Run gh auth login first"
STEP 2: Parse repository argument
The first token in $ARGUMENTS is the repository name (without the org prefix).
- Extract the first token as
repo_name - Set
repository = sablier-labs/{repo_name} - Remove the first token from $ARGUMENTS (remaining text is the issue description)
Example: /sablier:create-issue lockup "Bug in cliff streams" -> repository = sablier-labs/lockup
STEP 2.5: Parse optional flags
IF $ARGUMENTS contains --check:
- Remove
--checkfrom$ARGUMENTS - Set
check_mode = true - Continue to STEP 2.6
ELSE:
- Set
check_mode = false - Skip STEP 2.6 and continue to STEP 3
STEP 2.6: Check for similar issues (if --check flag present)
ONLY if check_mode = true:
-
Extract key terms from the remaining
$ARGUMENTS(issue description) -
Search for similar open issues (full-text search across title and body):
gh search issues "{key_terms}" --repo "sablier-labs/{repo_name}" --state open --limit 10 --json number,title,url -
IF similar issues found:
- Display the list of potentially related issues to the user
- Use
AskUserQuestionto prompt: "Similar issues found. Do you want to proceed with creating a new issue?"- Options: "Yes, create new issue" / "No, cancel"
- IF user selects "No": Exit command with message "Issue creation cancelled"
- IF user selects "Yes": Continue to STEP 3
-
IF no similar issues found:
- Inform user: "No similar issues found. Proceeding with issue creation."
- Continue to STEP 3
STEP 3: Apply labels
From content analysis, determine:
- Type: Primary category (bug, feature, docs, etc.)
- Work: Complexity via Cynefin (clear, complicated, complex, chaotic)
- Priority: Urgency (0=critical to 3=nice-to-have)
- Effort: Size (low, medium, high, epic)
- Scope: Domain area (only for sablier-labs/command-center)
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.
- 4d ago First seen · 197 lines · 12 tokens per session scan A 5d440fd1cbdd
create-issue is a command published in the GitHub repository sablier-labs/plugin-marketplace (7 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 1,518 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
project-recap
Generate a visual project recap for context switching.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).