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 skills add yarlson/yarstack --skill jira-issue-delivergit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/jira-issue-deliver)<a href="https://agentmods.dev/skills/yarlson/yarstack/jira-issue-deliver"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/jira-issue-deliver.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 | $0.00051 | $0.03732 |
| Opus 5 | $0.00026 | $0.01866 |
| Sonnet 5 | $0.00010 | $0.00746 |
| Haiku 4.5 | $0.00005 | $0.00373 |
Grade A, and why
jira-issue-deliver 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 7d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jira Issue Delivery
Own one Jira issue from first read to a reviewable pull request. Use the issue as the behavior contract, the repository as the implementation authority, and the current remote PR head to decide whether the work is complete.
Establish authority and completion
- Extract the Jira URL or key, repository, expected base branch, requested review systems, and terminal condition from the request.
- Confirm that the request explicitly permits code edits, commits, pushes, PR creation, marking the PR ready, review fixes, review replies, and thread resolution. Do not infer missing mutation authority from the issue alone.
- Read all applicable repository instructions before any repository or remote mutation. Obey repository-specific PR, title, test, release, and generated-file rules.
- Treat the task as complete only when current evidence proves all applicable conditions:
- the PR implements every in-scope acceptance criterion;
- the PR is open and ready for review, not a draft;
- the remote PR head matches the validated commit;
- every required check for that head passed or has a neutral result allowed by repository rules;
- each requested automated reviewer completed its review of the current remote PR head;
- each requested automated review thread has a recorded outcome supported by repository evidence, and each actionable thread is resolved;
- the PR title and body match the final diff and test evidence.
- Never merge, deploy, release, or transition the Jira issue under this skill. A ready, green, reviewed PR is the terminal state.
Keep this stage with the current agent. It becomes an orchestrator only if a later stage uses subagents.
Maintain autonomous progress
- Treat the full-delivery request as an instruction to continue without routine confirmation. Do not ask the user for a fact or choice that available evidence can resolve.
- Before asking a question, exhaust every applicable safe source:
- Jira fields, comments, links, attachments, and related issues;
- repository instructions, code, tests, documentation, configuration, and relevant history;
- installed CLI help, APIs, connectors, MCP tools, and authorized browser sessions;
- official web documentation and release notes for public technical facts.
- Never send private issue or repository data to public search. Search only the public terms needed to resolve the technical fact.
- When the evidence supports several valid approaches, choose the smallest reversible option that preserves current behavior and authorized scope. Record the assumption and proceed.
- Ask the user only when the unresolved answer would materially change required behavior or scope, available credentials or mutation authority are missing, authoritative requirements conflict, or every safe path would cause an irreversible or high-risk action.
- Ask one concise question. Briefly state what you checked, the remaining decision, and why it blocks progress. Continue all independent work while waiting when possible.
- Do not treat silence as authority. If the blocker prevents the terminal state, report it precisely instead of claiming completion.
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.
- 7d ago First seen · 175 lines · 51 tokens per session scan A 19eb7ab59c88
jira-issue-deliver is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 3,732 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 skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.