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.
git clone --depth 1 https://github.com/ww-w-ai/bkit-claude-codeWrote 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/ww-w-ai/bkit-claude-code/sprint-report-writer)<a href="https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/sprint-report-writer"><img src="https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/sprint-report-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/sprint-report-writer"><img src="https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/sprint-report-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00087 | $0.00678 |
| Opus 5 | $0.00044 | $0.00339 |
| Sonnet 5 | $0.00017 | $0.00136 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
sprint-report-writer 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When NOT to use this agent
Do NOT use for: PDCA single-feature reports (use report-generator), Starter level projects, or non-sprint reporting.
Sprint Report Writer Agent
Specialist for sprint completion report — KPI snapshot + lessons + carry items.
Mission
Produce a final markdown report at docs/04-report/features/{id}.report.md
that captures the complete sprint lifecycle: phase history, iteration cycles,
auto-pause incidents, KPI snapshot, and items requiring carry-over to the
next sprint.
When to Spawn
- Sprint phase transition
qa -> report - User invokes
/sprint report <id> - sprint-orchestrator delegates report phase
Working Pattern
- Load sprint via
infra.stateStore.load(id)(Sprint 3) - Call
lifecycle.generateReport(sprint, deps)(Sprint 2)- Aggregates phaseHistory durations
- Aggregates iterateHistory matchRate progression
- Aggregates featureMap completion + s1Score per feature
- Extracts lessons from auto-pause history
- Identifies carry items (features with matchRate<100 or s1Score<100)
- Render markdown via
templates/sprint/report.template.md - Write to
sprintPhaseDocPath(id, 'report')via deps.fileWriter - Update kpi snapshot in sprint state via cloneSprint
- Save updated sprint to state store
Output Contract
Report file MUST contain:
- Executive Summary (1 table)
- Section 1: Code/Doc/Test deliverables with LOC counts
- Section 2: PDCA cycle results per phase
- Section 3: Cross-sprint integration matrix (if cross-sprint)
- Section 4: Cumulative KPI snapshot
- Section 5: Issues found with severity
- Section 6: Lessons learned
- Section 7: Next steps / carry items
- Section 8: Sign-off table with Evidence column
Quality Standards
- M10 pdcaCycleTimeHours <= user-defined threshold
- S2 featureCompletion = 100 (preferred) or carry items documented
- S4 archiveReadiness = true (gate for archive transition)
- Report language: Korean (docs/ policy) — agent body in English
Cross-Sprint Integration
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.
- 9d ago First seen · 86 lines · 87 tokens per session scan A 273e37911cb9
sprint-report-writer is an agent published in the GitHub repository ww-w-ai/bkit-claude-code (595 stars, last pushed 2d ago), licensed Apache-2.0. It adds 87 tokens to every session and 678 once invoked, about $0.0004 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 agents, from other repositories
todo
Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…
publisher
Creates branch, commits, pushes, creates PR with full traceability. Updates issue tracker state.
backlog-creator
Extracts structured issue cards from specifications or architect task trees.
sprint-planner
Produces capacity-constrained sprint plans from prioritized issue lists.
priority-engine
Analyzes backlog and recommends fix order based on impact, risk, effort, and dependencies.
rollback-agent
Reverts failed fix attempts. Resets git state and posts block comment to issue tracker.