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/HigorAlves/orcWrote 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/higoralves/orc/jira-breakdown)<a href="https://agentmods.dev/commands/higoralves/orc/jira-breakdown"><img src="https://agentmods.dev/badge/commands/higoralves/orc/jira-breakdown/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/commands/higoralves/orc/jira-breakdown"><img src="https://agentmods.dev/badge/commands/higoralves/orc/jira-breakdown.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 | $0.00048 | $0.02178 |
| Opus 5 | $0.00024 | $0.01089 |
| Sonnet 5 | $0.00010 | $0.00436 |
| Haiku 4.5 | $0.00005 | $0.00218 |
Grade A, and why
jira-breakdown 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 9d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:jira-breakdown
A feature is coming and the team needs to swarm it. This command builds the Jira structure that makes that possible — per the orc:jira-hierarchy contract (invoke it first; it defines the levels, the micro-PRD sections, the mandatory child template, and the atomization rules). orc-jira-architect drafts the hierarchy; nothing is created until you approve the preview.
Arguments
- Free-form input — a feature brief, a
docs/prds/NNNN-*.mdpath, or a plan file. With--epic, input is optional (the epic's own description is the material). --epic <KEY>— attach children to this existing Epic instead of drafting a new one.--project <KEY>— Jira project. Resolution order: this flag →docs/agents/issue-tracker.md(written by/orc:setup) → the bound session ticket's project → ask.--team-size <n>— how many developers will work in parallel (drives atomization aggressiveness; default 3).--dry-run— stop after the preview; create nothing.
Workflow
Phase 0 — Detect + backend preflight
!orc-workspace-detect --banner
Context is injected above (ORC_* vars are exported — do not re-run detection).
Pick the Jira backend:
- Jira MCP tools present in the session (tool names matching
mcp__*jira*/mcp__*atlassian*with work-item write capability) → prefer them. - Else acli: invoke
orc:jira-cli, thenacli jira auth status. Non-zero → surface the auth-login hint and stop. - Neither → stop: point at
orc install/aclisetup and/orc:setupfor tracker config. Never fake a creation.
Phase 1 — Resolve project + parent Epic
- Resolve the project key per the order above. Validate
^[A-Z][A-Z0-9_]*$. - Resolve the Epic:
--epic <KEY>→ fetch it (acli jira workitem view <KEY> --jsonor MCP equivalent). It must exist and be active (status not Done/Closed/Resolved). Inactive or missing → surface and stop; children never attach to a dead Epic.- No
--epic→ search for candidates: JQLproject = <KEY> AND issuetype = Epic AND statusCategory != Donefiltered by input keywords. Then gate:
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.
- 9d ago First seen · 148 lines · 48 tokens per session scan A c57421d068e1
jira-breakdown is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 13d ago), licensed MIT. It adds 48 tokens to every session and 2,178 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 2026-08-31.
Other commands, from other repositories
interview
Interview & refine a spec, task, or spec file in-depth.
tracker-sync
Project a flow spec to a tracker (Linear/GitHub/GitLab/Jira) and reconcile body/status/comments two-way — projection, not coordination. NOT plan-sync (/flow-next:sync).
audit
Audit .flow/memory/ entries against the current codebase — Keep / Update / Consolidate / Replace / Delete / Harden per entry.
make-pr
Render a cognitive-aid PR body from flow-next state and open via gh.
pilot
Single-tick autonomous build-loop conductor (one item, one stage per invocation; pipeline.chainStages==on chains make-pr after a fresh qa verdict); --backlog/--auto widens it to triage the whole open backlog.
strategy
Create or maintain STRATEGY.md — repo-root anchor for target problem, approach, users, key metrics, and tracks.