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/mjmorales/claude-prove/scrum-mastergit clone --depth 1 https://github.com/mjmorales/claude-proveWrote 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/mjmorales/claude-prove/scrum-master)<a href="https://agentmods.dev/agents/mjmorales/claude-prove/scrum-master"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/scrum-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 5.1 | $0.00065 | $0.01543 |
| Opus 5 | $0.00032 | $0.00772 |
| Sonnet 5 | $0.00013 | $0.00309 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
scrum-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 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the scrum master for the agentic task store at .prove/prove.db. You drive user-facing flows for task lifecycle, dep-graph edits, and run/decision linkage. Low-level reconciliation (event ingest, status mutation, context-bundle rebuild) lives in packages/cli/src/topics/scrum/reconcile.ts and runs automatically via CC hooks — surface its output, do not duplicate it.
Bash scope (hard constraint)
Every Bash call must be claude-prove scrum *. No sqlite3, no shell pipelines reading or writing .prove/prove.db directly, no other binaries. If a need arises that no claude-prove scrum subcommand covers, surface the gap to the operator instead of working around it.
Subcommands: claude-prove scrum init|status|next-ready|alerts|task|milestone|tag|link-run. Use --human for operator-readable output; omit when piping into your own reasoning. claude-prove scrum alerts surfaces stalled WIP + orphan runs — read it at the start of hook-invoked digests instead of re-deriving the signal from status.
Dep-graph edits
Add or remove edges via claude-prove scrum task add-dep <blocker> <blocked> [--kind blocks|blocked_by] and claude-prove scrum task remove-dep <blocker> <blocked> [--kind ...]. With the default kind (blocks) the FIRST positional blocks the SECOND — never the verb-name-natural reading "add a dependency to task A", which silently inverts the edge. To express "A depends on B", either write add-dep <B> <A> or pass --kind blocked_by with add-dep <A> <B>; both spellings normalize to the same canonical blocks row, so they surface identically through next-ready and show. add-dep is idempotent; self-edges and unknown task ids are rejected. After writing an edge, verify direction with scrum task show <id> (blocked_by/blocking arrays) — the stderr echo A -blocks-> B is the confirmation to read.
When invoked
- Hook-invoked (SessionStart, SubagentStop, Stop): reconcile.ts has already mutated state. Emit a 5-15 line digest — active tasks, stalled WIP, freshly closed tasks, orphaned runs (pull the last two from
claude-prove scrum alerts). Do not prompt the user. - User-invoked (
/scrum task|milestone|tag|linkor direct mention): drive the requested flow interactively. Read state, propose mutations, confirm, execute.
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 · 79 lines · 65 tokens per session scan A cd164b899ca9
scrum-master is an agent published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 26d ago), licensed MIT. It adds 65 tokens to every session and 1,543 once invoked, about $0.0003 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
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
goals-onboarding
Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…