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-sweep-plan/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-sweep-plan)<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.
<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>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 | $0.00117 | $0.04142 |
| Opus 5 | $0.00059 | $0.02071 |
| Sonnet 5 | $0.00023 | $0.00828 |
| Haiku 4.5 | $0.00012 | $0.00414 |
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.
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)
state.jsonexists at{plan-dir}/state.json. If missing, refuse:"No state.json at {path}. Is this a remediation plan directory?".plan.mdexists at{plan-dir}/plan.md. If missing, refuse.schemaVersion ∈ {2, 3, 4}instate.json(2 and 3 are legacy schemas produced by the retired/backlog-sweep:planand/backlog-sweep:prepareroutes; 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.".ghCLI is on PATH (gh --versionexits 0). If not, refuse:"gh CLI not available — cannot query PR state. Install gh or run Step 1b manually.".gitCLI is on PATH (git --versionexits 0). If not, refuse.- Working tree is clean (
git status --porcelainis 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.". mainis the default branch and up to date withorigin/main. Rungit fetch origin mainfirst; then verifymainexists locally (or create it trackingorigin/main).
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 · -17 tokens per session 569ade215987
- 11d ago First seen · 236 lines · 134 tokens per session scan A dd68df9b5902
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.
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…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
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.