strava-mcp: Skill for Claude Code

.agents/skills/backlog-sweep/SKILL.md

backlog-sweep is a skill for Claude Code, Codex from ljcl/strava-mcp. It costs 100 tokens per session (1,633 once invoked), scanned A, original, MIT.

A workflow for checking every open GitHub issue against the current codebase. GitHub Issues are online records of bugs, tasks, and feature requests, and this workflow updates them when code changes make their details outdated.

In plain words
What is it for?
Use it to re-check an issue backlog after major changes, before selecting a batch of work, or when deciding whether an issue is still relevant.
Why use it?
Large refactors and breaking changes can leave issue links, file paths, line numbers, and assumptions incorrect. This finds that drift before developers plan or implement backlog work.

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 ljcl/strava-mcp's own configuration. It tells Claude Code and Codex how to work on strava-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 strava-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ljcl/strava-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/ljcl/strava-mcp/main/.agents/skills/backlog-sweep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ljcl/strava-mcp

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 backlog-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/ljcl/strava-mcp/backlog-sweep/github.svg)](https://agentmods.dev/skills/ljcl/strava-mcp/backlog-sweep)
Your own site
<a href="https://agentmods.dev/skills/ljcl/strava-mcp/backlog-sweep"><img src="https://agentmods.dev/badge/skills/ljcl/strava-mcp/backlog-sweep/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 backlog-sweep

Your own site · 80×15
<a href="https://agentmods.dev/skills/ljcl/strava-mcp/backlog-sweep"><img src="https://agentmods.dev/badge/skills/ljcl/strava-mcp/backlog-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,633 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 $0.00100 $0.01633
Opus 5 $0.00050 $0.00816
Sonnet 5 $0.00020 $0.00327
Haiku 4.5 $0.00010 $0.00163

Measured 5d ago against content hash d13cda4b0310, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

backlog-sweep 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.

.agents/skills/backlog-sweep/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backlog sweep

Re-ground the issue backlog in the current code. Issues are written against a snapshot of the repo; every epic, tool removal, or shell extraction that merges afterwards silently invalidates file paths, line numbers, dependency notes, and sometimes whole premises. This sweep finds and fixes that drift so the next implementer isn't working from fiction.

Issues live in GitHub Issues and are triaged on the "strava-mcp backlog" Project board (see docs/project.md for labels and board fields).

When to run

  • An epic, feat!: breaking change, or wide refactor just merged (the trigger that most reliably strands open issues).
  • Before picking a batch of backlog work, so effort estimates rest on reality.
  • On request ("triage the backlog", "is this issue still relevant?").

Procedure

  1. Gather. List all open issues, and skim recently closed ones — open issues cross-reference them ("coordinate with #N", "after #N lands"), and whether #N closed as completed or not planned changes what the open issue should say. Note recent merged PRs / releases since the last sweep for context.

  2. Verify each open issue against the code, not from memory. For every claim, grep or read the referenced file:

    • File paths and line numbers ("index.ts:256", "in main.tsx") — refactors move code; shared extractions relocate it to another package entirely.
    • Existence claims ("no X exists", "nothing handles Y") — the gap may have been closed by an unrelated PR.
    • Dependency framing ("once #N lands", "blocked on #N") — the dependency may have shipped (issue is now unblocked) or been closed not-planned (the coordination point no longer exists).
    • Data sources and APIs the issue builds on — tools/endpoints get removed (e.g. the v2.0 read-tool removal) and the issue must point at what remains.
    • Scope drift — a feature that shipped since filing may have changed what the issue needs to cover (e.g. a new default view widening an a11y issue).

Read the full file on GitHub · 115 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 Changed · +13 lines d13cda4b0310
  2. 8d ago First seen · 102 lines · 100 tokens per session scan A d14f5655cb20

Subscribe to this mod's changes

backlog-sweep is a skill published in the GitHub repository ljcl/strava-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 1,633 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.