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 agentmods add commands/kavanaghpatrick/ralph-parallel/statusgit clone --depth 1 https://github.com/kavanaghpatrick/ralph-parallelWhat 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 | $0.00007 | $0.01296 |
| Opus 5 | $0.00003 | $0.00648 |
| Sonnet 5 | $0.00001 | $0.00259 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
status 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Status
Shows the current state of parallel dispatch — which groups are active, task completion per group, and overall progress.
Parse Arguments
From $ARGUMENTS, extract:
- spec-name: Optional spec name (defaults to active spec)
- --json: Output raw JSON instead of formatted display
- --watch: Continuously poll and refresh status every 30 seconds
Step 1: Resolve Spec and Load State
1. Resolve spec (same logic as dispatch.md Step 1)
2. Read specs/$specName/.dispatch-state.json
- If missing: "No parallel dispatch active for '$specName'.
Run /ralph-parallel:dispatch to start parallel execution."
3. Read specs/$specName/tasks.md for current task states
4. Read specs/$specName/.ralph-state.json if exists
5. Read coordinatorSessionId from dispatch state
6. Compare against $CLAUDE_SESSION_ID env var:
- Both present + match: isCoordinator = true, display "Coordinator: this session"
- Both present + mismatch: isCoordinator = false, display "Coordinator: different session"
- coordinatorSessionId missing/null: isCoordinator = null, display "Coordinator: unknown (legacy)"
- $CLAUDE_SESSION_ID empty: isCoordinator = null, display "Coordinator: unknown (env unavailable)"
7. If status is "stale": Display stale notice:
"Dispatch STALE for '$specName' (reason: $staleReason, since: $staleSince)."
"Run /ralph-parallel:dispatch to re-dispatch, or /ralph-parallel:dispatch --abort to cancel."
Include staleSince, staleReason from dispatch state. Skip Steps 2-3 (no live team to query).
Step 2: Compute Progress
Primary source: TaskList (most reliable, real-time status)
Secondary source: tasks.md checkboxes, git log (fallback/supplementary)
1. QUERY TASKLIST: Use TaskList to get all tasks.
- Group tasks by owner (teammate name = group name)
- For each task, check status: pending, in_progress, completed
- Count completed vs total per group
2. CROSS-CHECK with tasks.md:
- Read tasks.md, match each group's spec task IDs
- Count [x] vs [ ] for group's tasks
- If TaskList and tasks.md disagree, prefer TaskList
3. DETECT ACTIVE WORK (secondary signal):
- Check git log for recent commits matching group's files
- This is supplementary — use for "Current activity" display line
4. CHECK DEPENDENCIES:
- Are blocking groups complete (via completedGroups in dispatch state)?
- Is this group unblocked and ready?
5. HANDLE VERIFY TASKS:
- verifyTasks may be objects {id, phase} or strings (legacy)
- For objects: extract id field for display
- For strings: use directly
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 · 151 lines · 0 tokens per session scan A f45b3b97609e
status is a command published in the GitHub repository kavanaghpatrick/ralph-parallel (7 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 1,296 once invoked, about $0.0000 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.