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 commands/quay/ai-helpers/implement-storyWrote 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/quay/ai-helpers/implement-story)<a href="https://agentmods.dev/commands/quay/ai-helpers/implement-story"><img src="https://agentmods.dev/badge/commands/quay/ai-helpers/implement-story.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 | $0.00010 | $0.05711 |
| Opus 5 | $0.00005 | $0.02856 |
| Sonnet 5 | $0.00002 | $0.01142 |
| Haiku 4.5 | $0.00001 | $0.00571 |
Grade A, and why
implement-story 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 — 744 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement JIRA Story
EXECUTE IMMEDIATELY: Implement JIRA story $ARGUMENTS. Do NOT print examples or describe what you will do - actually DO each step.
⚠️ CRITICAL: Tests are MANDATORY for all story implementations unless explicitly exempted.
EXECUTE THESE STEPS NOW FOR: $ARGUMENTS
START NOW: Run acli jira workitem view $ARGUMENTS immediately. Do not describe what you will do.
Step 1: Fetch Story from JIRA
Run this command NOW:
acli jira workitem view $ARGUMENTS
Extract from JIRA output:
- Story Title - The summary field
- Story Description - The description section (should contain implementation details)
- Story Type - The issue type
- Parent Epic - The epic link field (if present)
- Status - Current status
- Assignee - Who it's assigned to
Save story content:
Create .claude/implementation/<story-key>-context.md with:
- Story title as H1
- Full story description from JIRA
- Link to JIRA issue:
https://issues.redhat.com/browse/<story-key>
Step 2: Fetch Parent Epic (if exists)
If the story has a parent epic, fetch it:
acli jira workitem view <epic-key>
Save epic content:
Append to .claude/implementation/<story-key>-context.md:
- Epic title
- Epic description
- Epic scope (in-scope and out-of-scope)
- Link to epic
This provides broader context for implementation.
Step 3: Analyze Requirements and Detect Story Type
First, determine if this is a UI story by checking for these indicators:
UI Story Indicators:
- Story title contains:
[UI],[Frontend],UI Component,User Interface - Files to create/modify include paths like:
web/src/,frontend/,ui/,static/js/- Files ending in
.tsx,.jsx,.vue,.svelte - Component files, routes, pages
- Acceptance criteria mention:
- "User can click/see/interact"
- "Form validation", "Button", "Dialog", "Modal"
- "Responsive design", "Mobile view"
- "E2E tests", "Playwright tests", "Cypress tests"
- Technology mentions: React, Vue, Angular, TypeScript, PatternFly, Material-UI
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 · 744 lines · 10 tokens per session scan A 9193169a3133
implement-story is a command published in the GitHub repository quay/ai-helpers (3 stars, last pushed 20d ago), licensed MIT. It adds 10 tokens to every session and 5,711 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 2026-09-04.
Other commands, from other repositories
implement
Execute tasks from a track's implementation plan following TDD workflow.
shipwright-enhance
Add features to an existing Shipwright project.
verify-work
Verify feature, bug, UI, API, mobile, security, or deployment work against acceptance criteria.
workflow-implement
Exécuter la phase d'Implémentation - développement sprint avec TDD/BDD.
aqa-flow
Router workflow for test automation: routes to ui-aqa-flow, api-aqa-flow, or testgen-flow. Kept for backward compatibility.
sddp-implement-qc-loop
Command description: Run implement and QC in a continuous loop. Argument hint: [optional: feature directory or branch name] Command category: orchestration Prerequisites: spec, plan, tasks.