resilio-app: Skill for Claude Code

.agents/skills/vdot-baseline-proposal/SKILL.md

vdot-baseline-proposal is a skill for Claude Code, Codex from du-phan/resilio-app. It costs 56 tokens per session (1,154 once invoked), scanned A, original, MIT.

A proposal process for suggesting a runner’s VDOT baseline from exact race or assessment evidence. VDOT is a running-performance score used to estimate equivalent race ability and training levels.

In plain words
What is it for?
Reviewing qualifying race or personal-best evidence, writing a VDOT proposal, and identifying when there is not enough evidence for a valid baseline.
Why use it?
It keeps baseline decisions tied to confirmed times, distances, and dates instead of guessing from unrelated fitness or pace data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is du-phan/resilio-app's own configuration. It tells Claude Code and Codex how to work on resilio-app 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 resilio-app configures →

Reuse

Borrowing it

Nothing to install: this file belongs to du-phan/resilio-app. 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/du-phan/resilio-app/main/.agents/skills/vdot-baseline-proposal/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/du-phan/resilio-app

Made for: Claude Code, Codex.

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 vdot-baseline-proposal

README.md
[![agentmods](https://agentmods.dev/badge/skills/du-phan/resilio-app/vdot-baseline-proposal/github.svg)](https://agentmods.dev/skills/du-phan/resilio-app/vdot-baseline-proposal)
Your own site
<a href="https://agentmods.dev/skills/du-phan/resilio-app/vdot-baseline-proposal"><img src="https://agentmods.dev/badge/skills/du-phan/resilio-app/vdot-baseline-proposal/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 vdot-baseline-proposal

Your own site · 80×15
<a href="https://agentmods.dev/skills/du-phan/resilio-app/vdot-baseline-proposal"><img src="https://agentmods.dev/badge/skills/du-phan/resilio-app/vdot-baseline-proposal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,154 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 $0.00056 $0.01154
Opus 5.5 $0.00022 $0.00462
Sonnet 5.5 $0.00011 $0.00231
Haiku 4.5 $0.00006 $0.00115

Measured 2mo ago against content hash 207311a0598e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vdot-baseline-proposal 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 2mo 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.

.agents/skills/vdot-baseline-proposal/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baseline VDOT proposal

This is a proposal-only procedure. Write a new reviewable proposal file, but do not approve it or mutate the profile or planning state.

Evidence rules

  • Prefer an athlete-confirmed, recent race or personal best with an exact distance, elapsed time, and date.
  • An active exact-file VDOT approval in planning state is valid evidence and must be labeled as such.
  • A new VDOT approval cannot replace the dependency of an active plan. For a successor plan, complete the plan-renewal review and closure first.
  • Do not infer VDOT from easy pace, average activity pace, provider VO2 max, heart rate, native aerobic load, fitness/fatigue, or an arbitrary decay formula.
  • Do not use future performances or evidence outside the requested lookback.
  • If no qualifying evidence exists, return not_found and request an explicit manual athlete-approved value or route a non-injured athlete to the baseline-assessment-plan procedure.

Workflow

  1. Read the confirmed profile and approval state:

    poetry run resilio dates today
    poetry run resilio profile get
    poetry run resilio approvals status
    
  2. Evaluate current evidence:

    poetry run resilio vdot estimate-current --lookback-days <DAYS>
    
  3. For a newly confirmed race, calculate its value independently:

    poetry run resilio vdot calculate \
      --race-type <DISTANCE> \
      --time <ELAPSED_TIME> \
      --race-date <YYYY-MM-DD> \
      --as-of-date <ATHLETE_LOCAL_TODAY>
    
  4. For synchronized race evidence, retrieve the exact canonical source:

    poetry run resilio activity list \
      --since <PERFORMANCE_DATE> \
      --sport run
    

    Use only the matching record’s local_activity_id, elapsed_duration_seconds, distance_meters, activity_timezone, and source_external_fingerprint_sha256. Require a precise athlete confirmation that this result represents the complete official race distance. If those facts do not identify the confirmed race exactly, use an athlete-confirmed profile personal best or request clarification; do not invent a source binding or treat GPS distance as official distance.

Read the full file on GitHub · 133 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. 2mo ago First seen · 133 lines · 56 tokens per session scan A 207311a0598e

Subscribe to this mod's changes

vdot-baseline-proposal is a skill published in the GitHub repository du-phan/resilio-app (5 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 1,154 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

vdot-baseline-proposal compared with skills from other repositories

vdot-baseline-proposal next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vdot-baseline-proposaldu-phan/resilio-appSkill55d agoMITA56Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code