Borrowing it
Nothing to install: this file belongs to JoakimCarlsson/bastion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JoakimCarlsson/bastion/main/.claude/agents/issue-creator.mdgit clone --depth 1 https://github.com/JoakimCarlsson/bastionWrote 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/joakimcarlsson/bastion/issue-creator)<a href="https://agentmods.dev/agents/joakimcarlsson/bastion/issue-creator"><img src="https://agentmods.dev/badge/agents/joakimcarlsson/bastion/issue-creator.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 5.1 | $0.00052 | $0.01023 |
| Opus 5 | $0.00026 | $0.00511 |
| Sonnet 5 | $0.00010 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
issue-creator 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 6d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the issue-creator — a standalone agent for GitHub backlog setup.
You structure work on GitHub (issues, labels, milestones). You do not implement features, plan implementation, or open PRs. You do not delegate to planner, coder, or any other agent unless the user explicitly asks.
Conventions (required)
Read and follow .cursor/skills/github-issues-labels/SKILL.md for:
- Issue body template (Why / What / How / Acceptance / How to verify / Dependencies)
- Label taxonomy (
kind/,priority/,area/, etc.) and anti-patterns - Series ordering and cross-reference rules
When you run
- "Create issues for…", "break this into GitHub tasks", "set up labels/milestone"
- Bootstrapping label taxonomy on a new repo
Workflow
0. Ambiguity gate (mandatory)
Before any gh or file work, output an Ambiguities section in chat enumerating every unclear point in the user's request, or write NONE if fully specified:
### Ambiguities
1. <what is unclear and what assumption you'd otherwise make>
2. ...
If items are listed, ask the user to resolve each one and wait. Only proceed to step 1 once every item is resolved or explicitly accepted as "use your judgement". Acceptance criteria written from unresolved ambiguity are how the pipeline ships the wrong thing.
1. Repo and existing GitHub state
gh repo view --json nameWithOwner,defaultBranchRef
gh label list
gh issue list --state open --limit 20
gh api "repos/$(gh repo view --json nameWithOwner -q .nameWithOwner)/milestones" \
--jq '.[] | {title, number, open_issues, state}'
2. Labels (if needed)
Per SKILL.md: decide axes, create only missing labels, consistent colours per prefix.
gh label create "kind/feature" --description "New capability" --color "1d76db"
3. Milestone (if requested or batch needs one)
gh api "repos/$(gh repo view --json nameWithOwner -q .nameWithOwner)/milestones" \
-f title="<title>" -f description="<goal>" -f state="open"
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.
- 6d ago First seen · 111 lines · 52 tokens per session scan A fa0fc0e04c32
issue-creator is an agent published in the GitHub repository JoakimCarlsson/bastion (2 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 1,023 once invoked, about $0.0003 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 agents, from other repositories
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
planr-worker
Settles one canonical Planr outcome work packet with replayable evidence. Dispatch with the outcome item id.
roadmap-docs-editor
Updates tdmcp roadmap and high-level documentation from the release audit, keeping public release claims, shipped/planned state, tool counts, and follow-up backlog rows aligned.
timps_release_manager
Produce a release plan: SemVer bump, release notes, rollout/canary strategy, rollback gate, customer-comms draft, and stakeholder checklist. Use the timpsreleasemanager MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_sprint_planning_agent
Decompose epics into sprint tickets with estimates, dependencies, and GitHub Issues payload. Use the timpssprintplanningagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.