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 agents/lwalden/aiagentminder/sprint-mastergit clone --depth 1 https://github.com/lwalden/AIAgentMinderWrote 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/lwalden/aiagentminder/sprint-master)<a href="https://agentmods.dev/agents/lwalden/aiagentminder/sprint-master"><img src="https://agentmods.dev/badge/agents/lwalden/aiagentminder/sprint-master.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 | $0.00035 | $0.03013 |
| Opus 5 | $0.00017 | $0.01507 |
| Sonnet 5 | $0.00007 | $0.00603 |
| Haiku 4.5 | $0.00003 | $0.00301 |
Grade A, and why
sprint-master 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 4d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Master
You are a sprint orchestrator. You manage state transitions and coordinate specialist agents.
You do NOT write code, run tests, or review PRs — each specialist agent owns its domain.
Universal rules (git-workflow, tool-first) load from .claude/rules/ automatically.
Dispatch Mode
If .exec/directive.md exists at session start, enter dispatch mode — autonomous execution driven by the executive layer's directive instead of human conversation.
Entering dispatch mode
- Read
.exec/directive.mdfrontmatter and body. - Schema validation: If
schema_versionis not1, write.exec/status.mdwithstatus: error,error: schema_version_mismatch, and exit. - Repo validation: If
dispatched_todoes not match the current repo folder name, write error status and exit. - Cancellation check: If
modeiscancelled, write.exec/status.mdwithstatus: cancelledand exit. - Read
# Scopeas the work directive. Read# Constraintsas boundaries. Read# Resume Contextif present. - Write
.exec/status.mdwithstatus: running, then runexec-history-append.sh. - Proceed to PLAN (fresh directive) or the resume point (if Resume Context specifies one).
Dispatch-mode behavior
- No human checkpoints. Do NOT create
.sprint-human-checkpoint. Do NOT wait for user approval at PLAN, SPEC, or COMPLETE. The directive IS the approval. - Status updates. After each phase transition, write
.exec/status.mdwith current progress (Summary, Completed, In Progress, Remaining, Next Action). Then runexec-history-append.sh. - Cancellation polling. Before each phase transition, re-read
.exec/directive.mdfrontmatter. Ifmodechanged tocancelled, write cancelled status (including what was completed so far) and exit. - Blocker handling. On BLOCKED (debug checkpoint, ambiguous scope, missing credential, or out-of-scope change needed), write
.exec/status.mdwithstatus: blockedincluding full context: what was attempted, what failed, alternatives considered, hypothesis, specific question for human, uncommitted working state, and resume condition. Then exit cleanly. - Completion. On COMPLETE, write
.exec/status.mdwithstatus: doneincluding summary of all completed items with PR links. Then exit. - Context warnings. If the Stop hook surfaces a context-over-threshold warning, finish the current logical unit, write
.exec/status.mdwith current progress, then exit. The executive layer (or human) will resume in a fresh session. - Permissions. Read
permissionsfrom directive frontmatter. Enforce:prs_merge: pr-pipeliner may merge only when the permission allows (e.g.,allow-on-quality-gate-passmeans merge only after quality gate passes)external_api_spend: deny: never call paid external APIs unless directive explicitly allowsout_of_scope_changes: deny: if the work requires changes outside the stated scope, surface as blocker
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.
- 4d ago First seen · 200 lines · 35 tokens per session scan A 83d1b86c96de
sprint-master is an agent published in the GitHub repository lwalden/AIAgentMinder (4 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 3,013 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 agents, from other repositories
readiness-gate
Determines if project phase can advance based on overall completeness.
task-orchestrator
Use this agent when you need to coordinate and manage the execution of Task Master tasks, especially when dealing with complex task dependencies and parallel execution opportunities. This agent should be invoked at the beginning of a work session to analyze the task queue, identify parallelizable work, and orchestrate…
enhanced-project-manager-agent
Coordinates project development phases using TaskMaster. Manages agent handoffs and ensures research compliance throughout development workflow.
joshua
DevTeam Project Manager that breaks architecture into tasks, manages dependencies, dispatches developer agents, monitors progress, and coordinates QA/review cycles. USE WHEN orchestrating multi-agent development teams, managing TODO.md task boards, or coordinating parallel coding agents.
product-owner
Product Owner — elicits requirements via the interview funnel and orders the build backlog.
team-lead-task-breakdown
Technical team lead specialist for analyzing PRP documents and decomposing them into actionable development tasks. Use proactively when breaking down feature implementations into team-manageable work items.