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/zevtos/agentpipe/sprintgit clone --depth 1 https://github.com/zevtos/agentpipeWhat 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 | $0.00038 | $0.01729 |
| Opus 5 | $0.00019 | $0.00864 |
| Sonnet 5 | $0.00008 | $0.00346 |
| Haiku 4.5 | $0.00004 | $0.00173 |
Grade A, and why
sprint 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator. Your job is coordination, not implementation. You read context, delegate to agents, collect their output, and act on it. You do NOT analyze code, write code, or review code yourself — that is each agent's responsibility.
The pipeline is strict. Every phase is mandatory. You may not skip or merge phases, even for trivial issues.
Context
@CLAUDE.md
Arguments
$ARGUMENTS
Setup
Gather issues:
gh issue list --state open --assignee @me --json number,title,body,labels
If $ARGUMENTS specifies issue numbers (e.g. "12 15 20"), filter to those. If $ARGUMENTS is a label (e.g. "label:bugs"), filter by label. If $ARGUMENTS is empty, list all open and ask: "Which issues should I work through?"
Detect the repository's default branch:
DEFAULT_BRANCH=$(git remote show origin 2>/dev/null | sed -n '/HEAD branch/s/.*: //p')
DEFAULT_BRANCH=${DEFAULT_BRANCH:-main}
Use $DEFAULT_BRANCH as the base branch throughout this entire pipeline.
Present list and wait for confirmation. Then process each issue with the loop below.
Issue Loop (repeat for every issue)
Phase 1: Read Issue
gh issue view {NUMBER} --json number,title,body,comments,labels
Collect: title, body, referenced files, labels. Do not interpret or plan — just gather facts.
If the issue is ambiguous or missing acceptance criteria, post a comment asking for clarification and pause until resolved.
Phase 2: Architecture Plan — MANDATORY, NO EXCEPTIONS
Always run the architect agent, even for one-line fixes. No skipping.
Prompt to architect agent:
Issue #{NUMBER}: {TITLE}
Body:
{BODY}
Codebase context: [paste relevant file paths and signatures you found in Phase 1]
Your deliverables:
1. Root cause analysis (bug) OR feature gap analysis (feature)
2. Exact implementation plan — ordered list of file changes with specific line-level guidance
3. Data model changes (if any) — flag explicitly
4. API contract changes (if any) — flag explicitly
5. Risk assessment: what could break, what to test
6. Acceptance criteria: how to verify the fix is correct
Output format: numbered steps. Be specific — the implementor follows your steps literally.
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 · 269 lines · 38 tokens per session scan A 21a5f70b67cd
sprint is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,729 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 2026-08-30.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
speckit.auto
Automatically execute the four core phases of the Spec-Driven Development (SDD) pipeline: specify → plan → tasks → implement, in strict sequential order.
daily-priorities
Query DIGI Jira via the Atlassian MCP to build a prioritized daily work plan. The report has two parts: suggested priorities (the recommendation) and full context (everything you need to evaluate whether the suggestions are right and what else is on the docket).
OPSX: Bulk Archive
Archive multiple completed changes at once.
sync-linear
Sync current work with Linear ticket status.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).