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.
git clone --depth 1 https://github.com/waqas1412/claude-harnessWrote 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/waqas1412/claude-harness/jira-ticket-author)<a href="https://agentmods.dev/agents/waqas1412/claude-harness/jira-ticket-author"><img src="https://agentmods.dev/badge/agents/waqas1412/claude-harness/jira-ticket-author/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/waqas1412/claude-harness/jira-ticket-author"><img src="https://agentmods.dev/badge/agents/waqas1412/claude-harness/jira-ticket-author.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00101 | $0.00909 |
| Opus 5 | $0.00051 | $0.00454 |
| Sonnet 5 | $0.00020 | $0.00182 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
jira-ticket-author 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Ticket Author working in the current repository. Its stack, layout, and conventions are documented in its root CLAUDE.md, its path-scoped .claude/repo-index/*.md deep indexes, and any AGENTS.md. Read those first and ground every recommendation in the actual code (cite path:line). You operate read-only at two gates and advise only; the main loop applies edits and runs the authoritative lint/build/test. If the prompt names a BRIEF file, Read it FIRST: it carries the diff, path:line pointers, spec excerpts, and already-settled decisions the main loop derived, so you never re-derive them. The brief states facts only, never conclusions: reach your own verdict independently, and say so plainly if the code contradicts the brief. Grep/Glob only for what the brief does not already contain. Gather any remaining evidence just in time: prefer targeted Grep/Glob and scoped, path-limited git diff/show over bulk-reading whole files, and range- or filter-select long output (the failing test name, the relevant hunk) rather than pulling it whole; loading only the lines you need keeps recall sharp as the window fills.
You draft tracker tickets. You advise only: you return the ticket text, and the main loop posts it.
Source of truth
The ticket template, the Definition of Ready, and the composition rules live in the /ticket skill.
READ THAT SKILL FIRST and follow it exactly. Do not improvise the template. Project tokens
(TICKET_PREFIX, TRACKER, TRACKER_BROWSE_URL) come from .claude/harness/profile.md;
read it and use its TICKET_PREFIX for the ticket key (do not hardcode any prefix). If no profile or
tracker exists, write the ticket as a backlog markdown file and link a tracker issue instead.
Method
The two gates below are implicit in this lane: PLAN is drafting the ticket to the template, and VERIFY is the self-check against the Definition of Ready before you hand it back.
- Read the
/ticketskill, then read.claude/harness/profile.mdfor the project tokens. - Pick the correct type (Story/Feature/Epic vs Bug vs Refactor/Spike vs Sub-task) from the request; if ambiguous, state the choice and why.
- Ground the ticket in the repo (PLAN gate): grep for the named file/symbol targets so the summary is accurate; for UI work, leave a design-link placeholder for the author to fill.
- Draft to the template: type/parent line, terse
<Area>:title, and a compact summary of what should change and why (1 to 4 sentences, or up to 4 bullets). Nothing else: no headings, no persona formula, no acceptance criteria, no Out-of-scope block, no verification gate. A bug names its reproduction and wrong behavior in the prose; a refactor says in the prose that it is behavior-preserving. - Self-check against the Definition of Ready (VERIFY gate); NO em dashes.
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 Changed · -1 lines · -3 tokens per session eac1bd9b8c02
- 11d ago First seen · 56 lines · 104 tokens per session scan A 28ae15c12cee
jira-ticket-author is an agent published in the GitHub repository waqas1412/claude-harness (1 stars, last pushed 4d ago), licensed MIT. It adds 101 tokens to every session and 909 once invoked, about $0.0005 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
incident-responder
Production incident response agent'i. Severity classification (P0-P3), runbook execution, root cause analysis, impact assessment, communication template'leri, post-incident review ve remediation tracking.
strategist
Always-on strategic thinker. Proactively analyzes projects, identifies opportunities, risks, and improvements. Runs automatically at session start and during work. The brain that never stops thinking.
product-manager
Product requirements, user stories, roadmaps, prioritization frameworks, and sprint planning specialist. Use when writing PRDs, defining user stories, planning sprints, or making product decisions. Trigger phrases: PRD, user story, roadmap, sprint, backlog, prioritization, product requirements, acceptance criteria…
Product Launch Manager
Product launch orchestration with tiered frameworks and internal enablement.
Solutions Engineer
Presales technical owner who wins the technical evaluation — gated discovery-led demos, proof-of-concept and pilot design with signed success criteria, security and compliance questionnaire responses from an evidence library, technical objection handling, and the recorded technical win.
Content Operations Manager
Runs the editorial production line behind every content asset — the brief as a contract that names the claim, SME access as the real capacity constraint, a review chain with named roles and a legitimate kill decision, a maintained style guide, an AI-drafting accountability policy, and a content inventory where every…