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/dsifry/metaswarm/create-issuegit clone --depth 1 https://github.com/dsifry/metaswarmWhat 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 | $0.00000 | $0.00656 |
| Opus 5 | $0.00000 | $0.00328 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00066 |
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 2d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create GitHub Issue
Create a comprehensive, well-structured GitHub issue with embedded agent instructions for autonomous PR lifecycle management.
Usage
/create-issue [type] [description]
Arguments (optional - will prompt if not provided):
type:feature,bug, orrefactordescription: Brief description of the issue
Examples
# Interactive mode (prompts for all details)
/create-issue
# With type specified
/create-issue feature
# With type and description
/create-issue bug "Login fails when email contains plus sign"
What This Does
- Gathers context through interactive questions
- Generates comprehensive issue with all required sections:
- Problem/Feature specification with clear scope
- Technical specification (types, schemas, APIs)
- TDD Implementation Plan with test-first cycles
- Error handling matrix
- Files to create/modify
- Acceptance criteria checklist
- Agent Instructions for complete PR lifecycle
- Creates GitHub issue with appropriate labels
- Returns issue number for tracking
Steps
-
Activate the create-issue skill: Load and follow the create-issue skill definition.
-
Gather information through the interactive flow:
- Issue type (Feature/Bug/Refactor)
- Brief description
- Complexity estimate
- Related files/services
-
Generate issue content using appropriate template
-
Create issue via
gh issue create
Why Agent Instructions Matter
Every issue includes an "Agent Instructions" section that ensures:
- Complete lifecycle: From implementation through merge
- All comments addressed: Including trivial/nitpicks and out-of-scope
- Individual responses: Every thread gets a reply
- Iteration until done: Wait for reviews, iterate, don't auto-resolve
- Issue creation for deferred work: > 1 day = new issue
This makes issues self-contained work packets that agents can execute autonomously while maintaining quality standards.
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.
- 2d ago First seen · 105 lines · 0 tokens per session scan A 4a9f2a3a17e8
create-issue is a command published in the GitHub repository dsifry/metaswarm (407 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 656 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.