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 local-and-mcp-skill-name-deduplicationgit 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/local-and-mcp-skill-name-deduplication)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/local-and-mcp-skill-name-deduplication"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/local-and-mcp-skill-name-deduplication/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/local-and-mcp-skill-name-deduplication"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/local-and-mcp-skill-name-deduplication.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 | $0.00033 | $0.00418 |
| Opus 5 | $0.00016 | $0.00209 |
| Sonnet 5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
local-and-mcp-skill-name-deduplication 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 8d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Local-and-MCP Skill Name Deduplication
Domain: skill-listing Trigger: Apply when a listing surface combines commands from multiple registries or providers and must avoid announcing the same user-facing capability twice. Source Pattern: Distilled from reviewed command-surface, skill-discovery, and CLI capability implementations.
Core Method
Collect commands from each relevant source independently, then merge them into one announcement surface before any later filtering or formatting runs. Deduplicate the merged list by the stable user-facing command name rather than by source-specific IDs so identical capabilities from different providers collapse into one entry. This preserves broad coverage across local and remote registries while preventing the listing from double-counting equivalent commands simply because they were discovered through different backends.
Key Rules
- Load each source separately first so the merge step remains explicit and future sources can be added without rewriting downstream logic.
- Deduplicate on the stable presentation key the user actually sees, such as command name, not on internal source identifiers.
- Run deduplication before later listing filters or formatting so downstream budget and delta logic operate on the real surface area.
- Keep the single-source fast path when secondary sources are empty so the common case stays simple and cheap.
Example Application
If a coding agent can discover reusable skills from the current project and from connected MCP servers, gather both sets, merge them, and collapse entries that share the same slash-command name before rendering the skill catalog. The user sees one coherent listing instead of duplicates for the same command coming from different registries.
Anti-Patterns (What NOT to do)
- Do not concatenate multiple registries and announce them raw; duplicate command names will inflate the listing and confuse consumers.
- Do not deduplicate on backend-specific IDs when the real collision happens at the user-visible command name.
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.
- 8d ago First seen · 28 lines · 33 tokens per session scan A 29f096c59fe5
local-and-mcp-skill-name-deduplication is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 418 once invoked, about $0.0002 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 2026-09-03.
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.