agentmods.dev

coach-mcp: Skill for Claude Code

.claude/skills/acwr-recompute/SKILL.md

acwr-recompute is a skill for Claude Code from snoozelieb/coach-mcp. It costs 69 tokens per session (562 once invoked), scanned A, original, MIT.

A supervised migration tool for recalculating stored ACWR fitness history from daily training loads using the rolling 7-day to 28-day model. It reviews proposed changes and backs up the data before applying them.

In plain words
What is it for?
Use it to review and apply recalculated ACWR values for total training and each sport in fitness_history.json. It is intended for occasional historical corrections, not routine maintenance.
Why use it?
It corrects historical workload ratios after the calculation model changes or missing past loads are repaired, while protecting the existing coaching data. It avoids changing the separate CTL, ATL, and TSB training metrics.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is snoozelieb/coach-mcp's own configuration. It tells Claude Code how to work on coach-mcp 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 coach-mcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/recompute_acwr_history.py --check.

not rated 2repo +1 14d ago A scan 69 tokens original MIT
View source ↗ snoozelieb/coach-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to snoozelieb/coach-mcp. 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/snoozelieb/coach-mcp/main/.claude/skills/acwr-recompute/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/snoozelieb/coach-mcp

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 acwr-recompute

README.md
[![agentmods](https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/acwr-recompute/github.svg)](https://agentmods.dev/skills/snoozelieb/coach-mcp/acwr-recompute)
Your own site
<a href="https://agentmods.dev/skills/snoozelieb/coach-mcp/acwr-recompute"><img src="https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/acwr-recompute/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.

agentmods 80×15 button for acwr-recompute

Your own site · 80×15
<a href="https://agentmods.dev/skills/snoozelieb/coach-mcp/acwr-recompute"><img src="https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/acwr-recompute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 562 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 $0.00069 $0.00562
Opus 5 $0.00034 $0.00281
Sonnet 5 $0.00014 $0.00112
Haiku 4.5 $0.00007 $0.00056

Measured 10d ago against content hash 6d1d8ba446d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

acwr-recompute 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 10d 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.

.claude/skills/acwr-recompute/SKILL.md · 54 lines

What it actually says

Recomputing stored ACWR history (supervised)

scripts/recompute_acwr_history.py rewrites the acwr field of every snapshot entry in fitness_history.json — the total block AND every per-sport block — from raw daily_loads using the rolling 7d:28d model imported from coach.fitness (never a reimplementation). ctl/atl/tsb are left untouched: their EWMA scale is self-consistent and targets are tuned against it.

This is a supervised migration, not maintenance. It was built for the 2026-06-10 ACWR cutover; reach for it again only if the primary model changes or historical daily_loads were backfilled/repaired.

Procedure — in this order

  1. Timestamped backup first (execution rule for ANY migrating change to live coaching data — it is gitignored and irreplaceable):

    cp -r data "data-backups/backup-$(date +%Y%m%d-%H%M)"

  2. Dry-run and actually read it (default mode; writes nothing):

    python scripts/recompute_acwr_history.py --check

    Review the printed change list WITH the user — zone flips (optimal ↔ elevated, the "sweet spot" boundary, as labeled by classify_acwr_zone) are the changes that alter coaching behavior. Get explicit approval before applying.

  3. Apply:

    python scripts/recompute_acwr_history.py --apply

    --apply takes a one-time fitness_history.json.pre-acwr-cutover.bak beside the file (never overwritten — storage backup convention) and writes atomically/locked via coach.storage.

  4. Verify: re-run --check (should report no changes), then python -m pytest -q, then have the running MCP server reconnected so the snapshot serves recomputed values.

--data-dir path/to/data targets a non-default data directory (e.g. a restored backup for a rehearsal run — rehearse there when the change list is large).

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. 10d ago First seen · 54 lines · 69 tokens per session scan A 6d1d8ba446d3

Subscribe to this mod's changes

acwr-recompute is a skill published in the GitHub repository snoozelieb/coach-mcp (2 stars, last pushed 14d ago), licensed MIT. It adds 69 tokens to every session and 562 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.

Analytics and metrics
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens