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.
curl -O https://raw.githubusercontent.com/darylmcd/Roslyn-Backed-MCP/main/.claude/skills/reconcile-backlog-vs-issues/SKILL.mdgit clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCPWrote 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.
[](https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/reconcile-backlog-vs-issues)<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/reconcile-backlog-vs-issues"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/reconcile-backlog-vs-issues/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.
<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/reconcile-backlog-vs-issues"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/reconcile-backlog-vs-issues.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00122 | $0.03321 |
| Opus 5 | $0.00061 | $0.01661 |
| Sonnet 5 | $0.00024 | $0.00664 |
| Haiku 4.5 | $0.00012 | $0.00332 |
Grade A, and why
reconcile-backlog-vs-issues 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconcile Backlog vs GitHub Issues
You audit ai_docs/backlog.md against live GitHub Issue state. The backlog references Issues two ways:
- Reserved rows —
**Reserved — [gh #NNN](https://github.com/<owner>/<repo>/issues/NNN) (good first issue); skip in sweeps until contributor pickup.**— these rows are parked for outside contributors; sweeps must skip them. - Tracked-only rows —
[gh #NNN]({issue-url})somewhere in thedocell with no Reserved marker — the backlog row is the canonical work item, the Issue is just a public mirror.
When PRs merge, Issues close, contributors abandon, or labels drift, the two sides desynchronize. This skill walks every [gh #NNN] reference, queries gh issue view N, classifies the result, and emits a triage report. It does not mutate backlog.md or any Issue — the maintainer applies recommendations manually (or via /close-backlog-rows for the easy cases).
This skill is read-only. There is no destructive failure mode. The only side effects are network reads via gh.
Server discovery
This skill reads ai_docs/backlog.md and shells out to gh. Roslyn MCP is unrelated — no workspace loading, no analyzer calls. If you think you need Roslyn MCP, you are in the wrong skill.
Input
$ARGUMENTS accepts a single optional flag:
--stale-days N(default60) — theupdatedAtthreshold past which a Reserved row is classifiedreserved-stale(no contributor activity on the Issue for N days).
If $ARGUMENTS is empty, use the defaults.
Preconditions (HARD GATES — refuse if any fail)
ai_docs/backlog.mdexists at the repo root. If missing, refuse:"No ai_docs/backlog.md at repo root. Are you in the right repository?".ghCLI is on PATH (gh --versionexits 0). If not, refuse:"gh CLI not available — cannot query Issue state.".gh auth statussucceeds — the CLI is authenticated againstgithub.com. If not, refuse with thegh auth loginhint.
Workflow
Step 1 — Scan backlog.md for [gh #NNN] references
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.
- 2d ago Changed · -3 tokens per session cd59bb3015a5
- 10d ago First seen · 202 lines · 125 tokens per session scan A 9f4f5cb517fa
reconcile-backlog-vs-issues is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 3,321 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.