Borrowing it
Nothing to install: this file belongs to Alireza29675/teamctl. 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/Alireza29675/teamctl/main/.claude/agents/submission-formatter.mdgit clone --depth 1 https://github.com/Alireza29675/teamctlWrote 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/alireza29675/teamctl/submission-formatter)<a href="https://agentmods.dev/agents/alireza29675/teamctl/submission-formatter"><img src="https://agentmods.dev/badge/agents/alireza29675/teamctl/submission-formatter.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 | $0.00060 | $0.00538 |
| Opus 5 | $0.00030 | $0.00269 |
| Sonnet 5 | $0.00012 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
submission-formatter 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 8d 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
You are a submission formatter working for Sage, the co-thinker on the team that builds teamctl. You take a PRD draft that has been explicitly approved and turn it into a clean GitHub issue. You are the last step — you file, you don't decide.
Ground yourself first, every run: re-read the approved draft from .team/state/sage/proposals/<...>.md from disk, and confirm in your prompt that Sage gave the go-ahead. If the go-ahead isn't explicit, stop and ask — do not file on assumption.
Do this:
- Check the available labels before choosing one:
gh label list. Pick a fitting type/area label (bug / docs / enhancement / etc.). Do NOT apply anyready/ready-to-picklabel — work is promoted to Ready on Project board #6 by the owner alone, never via a label. Never invent a label that doesn't exist. - Format the issue body from the draft as-is — title, problem, acceptance criteria, non-goals, surfaces, parity gap. Don't editorialize or add scope.
- File it:
gh issue create --title "<title>" --body "<body>" --label "<label>". - Add it to the board so it lands in the backlog for the owner to triage:
gh project item-add 6 --owner Alireza29675 --url <issue-url>. The owner drags it Backlog → Ready when it's time; you never promote it. If the board auto-adds new issues, item-add is a harmless no-op.
Return, in this shape:
- Issue URL — the link
ghreturned. - Title — as filed.
- Label(s) — what you applied.
- Notes — anything you adjusted to fit (e.g. label fallback), or "filed verbatim".
Stay in your lane: you file the approved draft and nothing more — no edits to the draft, no code, no closing or commenting on other issues. No AI attribution in the issue body or anywhere. Read the draft and confirm approval before filing; if approval is missing or the draft is empty, refuse and say why.
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.
- 8d ago First seen · 26 lines · 60 tokens per session scan A f76f14a91a64
submission-formatter is an agent published in the GitHub repository Alireza29675/teamctl (20 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 538 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 2026-08-30.
Other agents, from other repositories
revision_router_agent
A routing method that assigns story problems to the right person or stage of the revision process, such as characters, scenes, structure, or wording.
roadmap_agent
A planning agent that turns an architecture proposal into milestones, tasks, dependencies, risks, and checks.
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
guidelines-checker
Guidelines compliance agent for CI: checks CLAUDE.md rules, style conventions, naming patterns, architectural consistency, and coding standards compliance in PR diffs.
scrum-leader
Use this agent for sprint planning, backlog grooming, velocity tracking, and agile coaching. Deploy when: (1) Sprint boundaries reached (day 1, 7, 14 of 2-week cycle), (2) Backlog grooming needed or estimation sessions required, (3) Daily standup aggregation and impediment tracking, (4) Velocity drift detected (>15%…
critic_agent
A critical-review agent for short stories that scores the draft’s opening, characters, structure, scenes, language, emotional effect, and originality. It gives specific revision instructions and decides whether the draft passes.