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 skill-listing-reset-on-real-skill-changesgit 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/skill-listing-reset-on-real-skill-changes)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/skill-listing-reset-on-real-skill-changes"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/skill-listing-reset-on-real-skill-changes/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/skill-listing-reset-on-real-skill-changes"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/skill-listing-reset-on-real-skill-changes.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 | $0.00034 | $0.00408 |
| Opus 5.5 | $0.00014 | $0.00163 |
| Sonnet 5.5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
skill-listing-reset-on-real-skill-changes 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 1mo 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: Skill Listing Reset on Real Skill Changes
Domain: command-surfaces
Trigger: Apply when a system tracks which skills have already been announced and must decide when that sent-state should be cleared.
Source Pattern: Distilled from reviewed command-surface and listing-control patterns.
Core Method
Tie announcement-state resets to real changes in the underlying skill inventory, such as plugin reloads or skill file changes on disk. Do not clear the sent-state for compaction, transcript recovery, or other conversation-level churn, because that would force expensive re-injections of essentially unchanged listings. This keeps listing deltas meaningful and avoids paying thousands of tokens to restate the same inventory after every context-management event.
Key Rules
- Reset the sent-state when the registry itself changes, not when the conversation representation changes.
- Keep reset triggers narrow and explicit, such as plugin reload or skill-file mutation hooks.
- Do not piggyback listing resets onto compaction, resume, or transcript maintenance paths unless those paths also change the actual registry.
- Clear any paired suppression flags together with the sent-state so the next genuine delta announcement starts from a clean slate.
Example Application
If a desktop agent reloads plugins and the available skill set changes, clear the sent-skill tracking map so the next listing can announce the new tools. If the conversation merely compacts or rehydrates from transcript, leave the sent-state alone so the agent does not spend tokens repeating an unchanged listing.
Anti-Patterns (What NOT to do)
- Do not reset announcement state on every compaction or replay event; that turns context maintenance into repeated full-list reinjection.
- Do not leave suppression flags out of sync with the reset; partial resets create confusing one-off gaps in later announcements.
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.
- 1mo ago First seen · 28 lines · 34 tokens per session scan A 6f9a003204e8
skill-listing-reset-on-real-skill-changes is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 408 once invoked, about $0.0001 per session on Opus 5.5. 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.
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log, then draft only the root pages that have meaningful content and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.