mcp-cli: Skill for Claude Code

.claude/skills/sprint-lessons/SKILL.md

sprint-lessons is a skill for Claude Code from theshadow27/mcp-cli. It costs 131 tokens per session (1,496 once invoked), scanned A, original, MIT.

A process for studying development-session history and turning it into ranked lessons about what worked, what failed, and how the operation changed.

In plain words
What is it for?
Grouping Claude Code sessions into sprints, classifying sessions, identifying trends, and producing actions for improving future work. A sprint is a defined period of development work.
Why use it?
It separates measured session facts, such as tokens, duration, and errors, from later interpretation so the analysis is repeatable.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is theshadow27/mcp-cli's own configuration. It tells Claude Code how to work on mcp-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to theshadow27/mcp-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/theshadow27/mcp-cli/main/.claude/skills/sprint-lessons/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/theshadow27/mcp-cli

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 sprint-lessons

README.md
[![agentmods](https://agentmods.dev/badge/skills/theshadow27/mcp-cli/sprint-lessons.svg)](https://agentmods.dev/skills/theshadow27/mcp-cli/sprint-lessons)
Your own site
<a href="https://agentmods.dev/skills/theshadow27/mcp-cli/sprint-lessons"><img src="https://agentmods.dev/badge/skills/theshadow27/mcp-cli/sprint-lessons.svg" alt="Measured on agentmods" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00131 $0.01496
Opus 5 $0.00066 $0.00748
Sonnet 5 $0.00026 $0.00299
Haiku 4.5 $0.00013 $0.00150

Measured 6d ago against content hash 513b2e38ef21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sprint-lessons 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.

The scan reads SKILL.md. This mod also ships 1 executable file (extract-sprint-sessions.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/sprint-lessons/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Lessons

Mines the full sprint session history for what worked, what broke, and how the operation has evolved — and turns it into ranked, implementable actions.

Two halves:

  • Extractor (extract-sprint-sessions.ts) — the data half. Runs locally, reads the raw session JSONL, and produces small deterministic digests. Facts (token totals, duration, error counts, orchestration signals) are computed here, not by an LLM, so they can't be hallucinated or recomputed.
  • Engine (../../workflows/sprint-lessons.js) — the judgment half. A multi-phase Workflow of haiku/sonnet agents that read the digests and produce structured classification, summaries, aggregates, and a trend.

The extractor writes a generated runner to /tmp that feeds the digest paths (grouped by sprint) into the engine via args. You invoke the runner; you never paste the data into a tool call.

How sessions map to sprints

Sprint boundaries are the commit timestamps of diary files (.claude/diary/YYYYMMDD.N.md), validated against .claude/sprints/sprint-N.md plan files — the same fencepost logic as the transcript archiver. Consecutive fenceposts tile the timeline, so every session lands in exactly one sprint. Sessions before the first diary ("legacy" era) are skipped.

Step 1 — extract (local)

# Full history:
bun .claude/skills/sprint-lessons/extract-sprint-sessions.ts

# Scope it (recommended first run — cheaper, validates the pipeline):
bun .claude/skills/sprint-lessons/extract-sprint-sessions.ts --since-sprint 60
bun .claude/skills/sprint-lessons/extract-sprint-sessions.ts --sprint 69 --sprint 70

Flags: --sprint N (repeatable), --since-sprint N, --window N (sprints per window, default 10), --max-sessions-per-sprint N (keep the N largest), --min-user-msgs N (default 1), --project-repo PATH.

It prints progress to stderr and a single JSON line to stdout:

{"runnerPath":"/tmp/sprint-lessons-…/run.js","runDir":"…","sprints":12,"sessions":140,"windowSize":10}

Read the full file on GitHub · 126 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 126 lines · 131 tokens per session scan A 513b2e38ef21

Subscribe to this mod's changes

sprint-lessons is a skill published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 2d ago), licensed MIT. It adds 131 tokens to every session and 1,496 once invoked, about $0.0007 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.