Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/quay/ai-helpersnpx agentmods add skills/quay/ai-helpers/workWrote 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/skills/quay/ai-helpers/work)<a href="https://agentmods.dev/skills/quay/ai-helpers/work"><img src="https://agentmods.dev/badge/skills/quay/ai-helpers/work.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 | $0.00049 | $0.01282 |
| Opus 5 | $0.00024 | $0.00641 |
| Sonnet 5 | $0.00010 | $0.00256 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
work 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 yesterday.
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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Loop — Single-Ticket Workflow
Implement JIRA ticket $ARGUMENTS from assignment to merge-ready PR in one
continuous loop.
Parse $ARGUMENTS: first token is the ticket key, --manual (if present)
sets manual stepping mode.
Initialize
bash .claude/scripts/tick-state.sh init $TICKET --mode $MODE
The Tick Loop
while state != COMPLETE:
1. READ — bash .claude/scripts/tick-state.sh read $TICKET
2. ACT — execute the handler for the current state
3. WRITE — bash .claude/scripts/tick-state.sh advance $TICKET <NEXT_STATE>
4. SLEEP — if DORMANT: the poll script blocks (0 tokens consumed)
5. PAUSE — if manual mode: ask user [c]ontinue / [s]kip / [i]nspect / [a]bort
6. LOOP — go back to step 1
CRITICAL: Do NOT stop between ticks. The only valid exit points are:
- State reaches COMPLETE
- Manual mode and user chooses [a]bort
- triage_attempts >= 3 (ask user for guidance)
State Handlers
ASSIGN
View the JIRA ticket, assign it, transition to ASSIGNED.
bash .claude/scripts/jira-ops.sh view $TICKET
bash .claude/scripts/jira-ops.sh assign $TICKET
bash .claude/scripts/jira-ops.sh transition $TICKET "ASSIGNED"
-> advance to BRANCH
BRANCH
Check backport requirement, create feature branch, load area docs.
bash .claude/scripts/jira-ops.sh check-version $TICKET
git checkout ${PRIMARY_BRANCH:-master} && git pull origin ${PRIMARY_BRANCH:-master}
git checkout -b $TICKET-short-description
bash .claude/scripts/tick-state.sh set $TICKET branch "<branch-name>"
-> advance to IMPLEMENT
IMPLEMENT
Read AGENTS.md plus area docs. Write code, create tests, handle edge cases.
-> advance to TEST
TEST
Run quality checks and tests:
bash .claude/scripts/format-and-lint.sh
If tests fail: fix and re-run. Stay in TEST until all pass. -> advance to COMMIT
COMMIT
Stage and commit:
git add <specific files>
git commit -m "<subsystem>: <what changed> ($TICKET)"
If pre-commit hooks fail: fix, re-stage, new commit. Stay in COMMIT until success. -> advance to PR_CREATE
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.
- yesterday First seen · 161 lines · 49 tokens per session scan A 05cd34024328
work is a skill published in the GitHub repository quay/ai-helpers (3 stars, last pushed 19d ago), licensed MIT. It adds 49 tokens to every session and 1,282 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…
cyrus-setup-repository
Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.
github-sync
Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.
github-sync-helper
General GitHub basic operations + automation for GitHub platform objects (Issues/Labels/Milestones/Releases/Actions) in the Minis environment. This skill must be triggered when the user mentions any basic Git/GitHub operation or workflow, including "how to use GitHub," clone, init, remote, branch, commit, push, pull…