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 per-agent-skill-listing-dedupegit 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/per-agent-skill-listing-dedupe)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/per-agent-skill-listing-dedupe"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/per-agent-skill-listing-dedupe/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/per-agent-skill-listing-dedupe"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/per-agent-skill-listing-dedupe.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 | $0.00032 | $0.00393 |
| Opus 5 | $0.00016 | $0.00197 |
| Sonnet 5 | $0.00006 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
per-agent-skill-listing-dedupe 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 6d 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.
What it actually says
SKILL: Per-Agent Skill Listing Dedupe
Domain: attachment-pipeline Trigger: Use when a multi-agent runtime must announce new skills or capabilities without one thread's deltas erasing another thread's initial listing. Source Pattern: Distilled from reviewed per-agent capability-announcement tracking implementations.
Core Method
Track which skill names were already sent to each agent separately rather than globally. Each agent or thread gets its own seen-set keyed by a stable agent identity, so the main thread announcing a listing does not make every subagent believe it already saw the same surface. When building the delta list for a given agent, compare only against that agent's set and update that set after sending.
Key Rules
- Store a distinct seen-set per agent or thread, including a stable identity for the main thread.
- Filter outgoing skill deltas against the target agent's seen-set, not a global pool.
- Keep the per-agent seen-set alive for the lifetime of that agent so resumes and follow-up turns reuse its own state.
- Update the agent's seen-set immediately after sending new skills so later deltas stay accurate.
Example Application
If a subagent is spawned in the middle of a long-running coding session, start it with its own empty seen-set. Even though the main thread already announced the skill surface, the subagent still gets a proper first-turn listing because its own history starts blank.
Anti-Patterns (What NOT to do)
- Do not keep one global seen-set; that makes every new agent believe everything was already announced.
- Do not let one agent reuse another agent's seen-set; cross-agent sharing collapses the whole point of per-thread deltas.
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.
- 6d ago First seen · 28 lines · 32 tokens per session scan A 56456bd9a397
per-agent-skill-listing-dedupe is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 393 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.