agentmods.dev

retro

retro is a skill for Claude Code from Maximumsoft-Co-LTD/claude-flightdeck. It costs 110 tokens per session (2,244 once invoked), scanned A, original, MIT.

A workflow for closing a sprint—a fixed period of planned development work—and recording what the team learned.

In plain words
What is it for?
Use it to close sprints, write retrospectives, promote lessons into rules, and archive old sprint records.
Why use it?
It turns completed work and lessons into immediate cleanup and possible project rules instead of leaving problems unresolved.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

not rated 2 3mo ago A scan 110 tokens original MIT
View the source file Maximumsoft-Co-LTD/claude-flightdeck
Install

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.

agentmods
npx agentmods add skills/maximumsoft-co-ltd/claude-flightdeck/retro
Any agent
npx skills add Maximumsoft-Co-LTD/claude-flightdeck --skill retro
Clone the repo
git clone --depth 1 https://github.com/Maximumsoft-Co-LTD/claude-flightdeck

Made for: Claude Code.

Wrote 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.

agentmods badge for retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/maximumsoft-co-ltd/claude-flightdeck/retro.svg)](https://agentmods.dev/skills/maximumsoft-co-ltd/claude-flightdeck/retro)
Your own site
<a href="https://agentmods.dev/skills/maximumsoft-co-ltd/claude-flightdeck/retro"><img src="https://agentmods.dev/badge/skills/maximumsoft-co-ltd/claude-flightdeck/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.02244
Opus 5 $0.00055 $0.01122
Sonnet 5 $0.00022 $0.00449
Haiku 4.5 $0.00011 $0.00224

Measured 5d ago against content hash 5c631988bedb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

retro 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 5d 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.

core/.claude/skills/retro/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/retro — Sprint Close · Rule Ratification · Archive

Announce: Using /retro …

The retro fixes problems immediately — it does not just document them. Old /ratify-rules and /archive are gone; use /retro ratify and /retro archive.

Token budget

  • One Read of docs/project/sprints/S<N>/tasks.md (limit: 400) — the primary input (the board holds the live mini-retros).
  • One Read of docs/project/backlog.md — for the audit + the highest F#### ID.
  • scripts/backlog.sh sweep + index — sprint-close backlog hygiene (closed ## Active rows → cold archive; index regen). Deterministic bash, 0 LLM tokens.
  • Grep for everything else (lesson recurrence, candidate rules, sprint scan).
  • Grep one section of ../../rules/brain-hot.md (ratify mode) — never full-Read.

Mode 1 — /retro (sprint close + auto-chain ratify)

The live per-task mini-retros inside docs/project/sprints/S<N>/tasks.md are the PRIMARY input. The full retro lands in docs/project/sprints/S<N>/retro.md. Two HARD gates block close.

  1. Read the board — docs/project/sprints/S<N>/tasks.md. Missing/empty = process loss; flag it in the retro.
  2. Read docs/project/backlog.md — note the highest existing F####; open rows are candidates for reconciliation at the audit gate.
  3. Scan git log since sprint open for each touched repo.
  4. Cross-cutting drift — grep for invariants (contract drift, schema drift, observability gaps). Each drift = a finding.
  5. Gather top wins + top issues (ask the user, or "auto").
  6. Create docs/project/sprints/S<N>/retro.md from the template below.
  7. Classify every action item — fix NOW (this commit) vs defer (backlog row or follow-up).
  8. Execute every "fix now" item — do NOT commit the retro until they land (update affected skills + rules in the same commit).

HARD GATE — Backlog audit (drift blocks close):

scripts/backlog.sh check        # Status enum + size cap — must exit 0
scripts/backlog.sh reconcile    # advisory: wip rows that look already-closed in S<N>

check must pass. Resolve every reconcile flag (set genuinely-shipped rows to done S<N>; the sweep below moves them out). Cite: Backlog audit: check ✓ · <N> reconcile flag(s) resolved.

Read the full file on GitHub · 156 lines

Changes

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.

  1. 5d ago First seen · 156 lines · 110 tokens per session scan A 5c631988bedb

Subscribe to this mod's changes

retro is a skill published in the GitHub repository Maximumsoft-Co-LTD/claude-flightdeck (2 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 2,244 once invoked, about $0.0006 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.

Project managementagenticai-workflowclaude-codecontrol-planedeveloper-toolsllm-agents
Related

Other skills, from other repositories

vc-generate-phase-program

Generate kickoff artifacts for a multi-phase program: umbrella plan, Program Goal Charter, session-goal block, per-phase plan stubs, and the 7-step per-phase inner loop reference.

withkynam/vibecode-pro-max-kit · 44 tokens

vc-intent-clarify

Clarify intent before RIPER-5 phase delegation. Scores ambiguity (4 signals); generates structured multi-choice questions for Tier 2. Two-mode: SIMPLE and DEEP.

withkynam/vibecode-pro-max-kit · 42 tokens

vc-agent-strategy-compare

Evaluate 4 execution strategies (sequential, parallel-subagents, workflow, agent-team) for a phase or fan-out task. Outputs 7-signal score table, agent count math, cost guards, and strategy recommendation.

withkynam/vibecode-pro-max-kit · 52 tokens

vc-autoresearch

Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit. Shared loop primitive for PVL, EVL, and standalone quality runs.

withkynam/vibecode-pro-max-kit · 40 tokens

vc-generate-closeout

Generate the post-EXECUTE closeout packet for a plan or phase. Includes archive-readiness classification, drift signal scoring, commit checkpoint recommendation, and move-on next-state recommendation.

withkynam/vibecode-pro-max-kit · 42 tokens

vc-validate-findings

Use when running VALIDATE V2-V3 fan-out. Two-layer investigation (4 dimension agents + per-section feasibility agents) synthesized into PASS/CONDITIONAL/BLOCKED net gate. Strategy-agnostic.

withkynam/vibecode-pro-max-kit · 49 tokens