Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ychampion/cskill-agents --skill background-marketplace-reconciliationgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/background-marketplace-reconciliation)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/background-marketplace-reconciliation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/background-marketplace-reconciliation/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/ychampion/cskill-agents/background-marketplace-reconciliation"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/background-marketplace-reconciliation.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 | $0.00027 | $0.00435 |
| Opus 5 | $0.00014 | $0.00217 |
| Sonnet 5 | $0.00005 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
background-marketplace-reconciliation 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 11d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Background Marketplace Reconciliation
Domain: tool-orchestration Trigger: Use when you need to reconcile declared plugin marketplaces or source registries without blocking startup or the main command loop. Source Pattern: Distilled from reviewed plugin-source reconciliation and background install lifecycle implementations.
Core Method
Diff the declared marketplace or plugin-source configuration against the current cached state before doing any network work. Seed UI state with a pending entry for every source that needs installation or update, then run the actual reconciliation in the background. As progress events arrive, map them onto visible install states so the product can show spinners, success, and failure per source without freezing the main UI. When reconciliation finishes, clear stale caches and branch on the outcome so new installs, updates, and failures each trigger the right downstream behavior.
Key Rules
- Populate visible state with
pendingrows before the async work begins so the UI can render progress immediately. - Use progress callbacks to update each source row (
installing,installed,failed) and attach any error text for diagnostics. - Keep analytics/logging around the whole operation so you know how many installed/updated/failed entries returned.
- After the promise resolves, clear caches and trigger refresh or flag-for-refresh decisions rather than leaving stale extension state behind.
Example Application
For a new agent UI that adds curated plugin sources, apply this pattern whenever sources need to be cloned or updated in the background so the UI gets per-source spinners and the rest of the agent remains responsive.
Anti-Patterns (What NOT to do)
- Do not block the main thread until marketplace reconciliation finishes; it should happen behind the scenes with status rows.
- Do not start reconciling without seeding the UI state—users must see which marketplaces are pending.
- Avoid treating updates and fresh installs the same way; they often require different downstream actions (live refresh vs. manual refresh notification).
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.
- 11d ago First seen · 31 lines · 27 tokens per session scan A 76ecceddb735
background-marketplace-reconciliation is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 435 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.