Roslyn-Backed-MCP: Skill for Claude Code

.claude/skills/reconcile-backlog-sweep-plan/SKILL.md

reconcile-backlog-sweep-plan is a skill for Claude Code from darylmcd/Roslyn-Backed-MCP. It costs 117 tokens per session (4,142 once invoked), scanned A, original, MIT.

A bookkeeping workflow for updating a backlog plan after its pull requests have been merged or closed. A backlog is a list of planned work, and a pull request is a proposed code change for review.

In plain words
What is it for?
Use it to inspect backlog plan files, check GitHub pull-request status, update initiative states, and submit the reconciliation as a short-lived branch.
Why use it?
It prevents completed initiatives from being treated as still pending and helps choose the next real item to work on.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

This is darylmcd/Roslyn-Backed-MCP's own configuration. It tells Claude Code how to work on Roslyn-Backed-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 Roslyn-Backed-MCP configures →

Part of the roslyn-mcp plugin — 44 skills, 5 agents, 2 hooks, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to darylmcd/Roslyn-Backed-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/darylmcd/Roslyn-Backed-MCP/main/.claude/skills/reconcile-backlog-sweep-plan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCP

Made for: Claude Code.

Or install roslyn-mcp, the plugin that ships this one along with the rest of its 44 skills, 5 agents, 2 hooks, 2 MCP servers.

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 reconcile-backlog-sweep-plan

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/reconcile-backlog-sweep-plan"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/reconcile-backlog-sweep-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,142 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 $0.00117 $0.04142
Opus 5 $0.00059 $0.02071
Sonnet 5 $0.00023 $0.00828
Haiku 4.5 $0.00012 $0.00414

Measured 2d ago against content hash 569ade215987, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

reconcile-backlog-sweep-plan 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 2d 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/reconcile-backlog-sweep-plan/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reconcile Remediation Plan

You are a plan-state reconciler. Your job is to walk a remediation plan's state.json and plan.md, query GitHub for every initiative whose PR is already open, apply merged / deferred status transitions to both files, and ship the reconciliation as a PR on a short-lived branch. The installed name /reconcile-backlog-sweep-plan is retained only for compatibility.

This skill does not pick new work and does not execute initiatives. It is a bookkeeping pass that runs between PR waves.

Server discovery

This skill edits repository files and shells out to gh + git. Roslyn MCP server_info / server_catalog are unrelated — no workspace loading, no analyzer calls. If you think you need Roslyn MCP, you are in the wrong skill.

Input

$ARGUMENTS optionally names the plan directory (relative to repo root, e.g. ai_docs/plans/20260417T120000Z_backlog-remediate). The _backlog-sweep directory suffix is a historical compatibility label. If omitted, enumerate the union of ai_docs/plans/*_backlog-remediate/ and legacy ai_docs/plans/*_backlog-sweep/ directories. Classify every candidate under one terminal rule (terminal = completed: true AND every initiative status in {merged, obsolete, deferred} — the canonical terminal set in ~/.claude/prompts/backlog-remediate-rules.md), then select the oldest non-terminal plan across the combined set (FIFO drain). This mirrors /backlog-remediate plan selection — do NOT prefer one suffix or default to newest-by-name, either of which can strand an older non-terminal plan whose in-review PRs never get reconciled.

Preconditions (HARD GATES — refuse if any fail)

  1. state.json exists at {plan-dir}/state.json. If missing, refuse: "No state.json at {path}. Is this a remediation plan directory?".
  2. plan.md exists at {plan-dir}/plan.md. If missing, refuse.
  3. schemaVersion ∈ {2, 3, 4} in state.json (2 and 3 are legacy schemas produced by the retired /backlog-sweep:plan and /backlog-sweep:prepare routes; 4 is the current default — all three remain valid per the canonical field contract). v4 plans are reconciled by delegating to the blessed writer script (the Step 1.2 v4 fast path); 2/3 plans use the manual path below. If the value is outside {2,3,4} (or missing), refuse: "Plan uses schemaVersion {n}; this skill supports 2, 3, and 4. Re-run /backlog-remediate to regenerate.".
  4. gh CLI is on PATH (gh --version exits 0). If not, refuse: "gh CLI not available — cannot query PR state. Install gh or run Step 1b manually.".
  5. git CLI is on PATH (git --version exits 0). If not, refuse.
  6. Working tree is clean (git status --porcelain is empty) OR the only dirty paths are the two files this skill will edit (state.json + plan.md). If dirtier, refuse: "Working tree has unrelated changes — commit or stash before reconciling.".
  7. main is the default branch and up to date with origin/main. Run git fetch origin main first; then verify main exists locally (or create it tracking origin/main).

Read the full file on GitHub · 236 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. 2d ago Changed · -17 tokens per session 569ade215987
  2. 11d ago First seen · 236 lines · 134 tokens per session scan A dd68df9b5902

Subscribe to this mod's changes

reconcile-backlog-sweep-plan is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 4,142 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.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens

magpie-security-issue-import-from-md

Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.

apache/magpie · 73 tokens