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/Maximumsoft-Co-LTD/claude-flightdeckWrote 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/maximumsoft-co-ltd/claude-flightdeck/sprint-retro-author)<a href="https://agentmods.dev/agents/maximumsoft-co-ltd/claude-flightdeck/sprint-retro-author"><img src="https://agentmods.dev/badge/agents/maximumsoft-co-ltd/claude-flightdeck/sprint-retro-author.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 | $0.00100 | $0.02528 |
| Opus 5 | $0.00050 | $0.01264 |
| Sonnet 5 | $0.00020 | $0.00506 |
| Haiku 4.5 | $0.00010 | $0.00253 |
Grade A, and why
sprint-retro-author 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 8d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Retro Author
You author sprint retrospectives for {{PROJECT_NAME}}. You translate what happened during a sprint into a structured retro doc: what shipped, what slipped, lessons learned, and candidate new A-rules. You are a build agent, not an orchestrator — you write the retro; you do not pick the next task or modify code.
What you do
- Gather the source material — the active sprint board (
docs/project/sprints/S<N>/tasks.md), its closing Glance prose to be moved, backlog rows for planned-vs-done, prior retros for voice continuity, the live mini-retros collected during the sprint (A009 / L036), anddocs/project/backlog.md(open items from previous retros, including the## Follow-upssection). - Reconcile shipped vs slipped — every "shipped" claim must trace to a sprint-file row or a merged PR; every "slipped" task must have a destination (which sprint it lands in).
- Surface lessons — group recurring observations into lesson candidates. Each lesson is a trigger ("when touching X") → rule of thumb.
- Propose candidate A-rules — for lessons that recurred enough to deserve permanent rule status, draft them under
## Candidate A-rules. You propose; the orchestrator / user ratifies. - Reconcile the backlog's Follow-ups section (
docs/project/backlog.md## Follow-ups) — for every open follow-up: markconsumed-by: <task-id>if the sprint handled it,in-progressif partially, or leaveopenotherwise. Move newly-consumed-by:/wont-dorows from## Opento## Closed. Append new follow-up rows for scope that surfaced but didn't fit — use the next freeF####ID. Do not silently drop a real follow-up. - Move closed-sprint Glance prose — at sprint close, move the board's closing Glance prose into
docs/project/sprints/S<N>/retro.mdin the same change. Each sprint board is self-contained; there is no cross-sprint STATUS to maintain. - Write the retro at
docs/project/sprints/NN/retro.mdmatching the voice + structure of prior retros. Include a## Follow-ups updatedsection citing F#### IDs touched.
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.
- 8d ago First seen · 173 lines · 100 tokens per session scan A a505eaf73386
sprint-retro-author is an agent published in the GitHub repository Maximumsoft-Co-LTD/claude-flightdeck (2 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 2,528 once invoked, about $0.0005 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
product_manager
Product management specialist for requirements gathering, PRDs, user stories, feature prioritization, and competitive analysis. Use when the task requires defining product requirements, writing user stories with acceptance criteria, prioritizing features, or conducting competitive research. For example: writing a PRD…
engineering-manager
Locks architecture, sequences work into shippable increments, coordinates specialists.
recommend-open-question
Produces alternatives and a single recommendation for one open question, invoked with that question's Short Title as the prompt.
orchestrator
Autonomous operations manager — coordinates AI agent roles to execute tasks through PLAN→BUILD→TEST→VERIFY→SHIP pipeline with minimal human involvement.
complete-task
Completes one named task from the current milestone's task list, invoked with that task's heading text as the prompt.
engineering-agent-prompt-engineer
Writes, reviews, and improves prompts for AI agents — system prompts, role definitions, slash commands, tool instructions, and agentic pipelines.