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/hundia/autospec/sprint-rungit clone --depth 1 https://github.com/Hundia/autospecWrote 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/hundia/autospec/sprint-run)<a href="https://agentmods.dev/commands/hundia/autospec/sprint-run"><img src="https://agentmods.dev/badge/commands/hundia/autospec/sprint-run.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 | $0.00000 | $0.01898 |
| Opus 5 | $0.00000 | $0.00949 |
| Sonnet 5 | $0.00000 | $0.00380 |
| Haiku 4.5 | $0.00000 | $0.00190 |
Grade A, and why
sprint-run 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 6d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Run
Execute an entire sprint end-to-end: plan → implement → QA → docs → close.
Usage
/sprint-run [sprint_number]
Example: /sprint-run 4
Instructions
Execute the sprint through 8 phases. Get user confirmation after Phase 1 before proceeding.
Phase 1: Sprint Briefing
- Read
specs/backlog.md— find the target sprint - Read ALL relevant spec files referenced by the sprint's tickets
- Read ALL relevant
docs/sections — docs are the authoritative source. Include these paths in agent briefs so agents read them before implementing. - Build execution plan:
- Order tickets by dependencies (DAG sort)
- Identify parallelizable batches (tickets with no mutual dependencies)
- Map each ticket to recommended model (FinOps)
- Present plan to user and WAIT for confirmation before proceeding
Output:
## Sprint X: [Name] — Execution Plan
### Tickets (ordered by dependencies)
| # | Ticket | Owner | Model | Dependencies | Batch |
|---|--------|-------|-------|-------------|-------|
### Estimated Batches
- Batch 1 (parallel): X.1, X.2, X.3
- Batch 2 (sequential): X.4 (depends on X.1)
- Batch 3 (parallel): X.5, X.6
Shall I proceed with execution?
DEFAULT Execution Pattern: Orchestrator + Sonnet Agents
ALWAYS use this pattern. Opus orchestrates, Sonnet agents implement. This keeps the orchestrator's context clean and is FinOps efficient.
-
Orchestrator (Opus 4.6) — never implements directly. Instead:
- Writes
agents/sprint-X-brief.mdwith full context package - Includes relevant
docs/file paths in the brief so agents read them FIRST - Spawns
Agent(subagent_type=general-purpose, model="sonnet")for implementation - Reviews results, merges, then spawns next batch
- Writes
-
Sprint Agent (Sonnet 4.6) — reads brief, implements all tickets:
- Reads
agents/sprint-X-brief.mdfor full context - Reads ALL
docs/files listed in the brief BEFORE writing any code - Executes tickets per
execute-ticket.mdconventions - Updates
specs/backlog.md(🔲→✅), docs/, sprint summary - If any code written is NOT documented in
docs/, creates/updates the relevant doc file
- Reads
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.
- 6d ago First seen · 201 lines · 0 tokens per session scan A 861af51e559a
sprint-run is a command published in the GitHub repository Hundia/autospec (4 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,898 tokens. 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.