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 aggregated-change-signal-returngit 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/aggregated-change-signal-return)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/aggregated-change-signal-return"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/aggregated-change-signal-return/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/aggregated-change-signal-return"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/aggregated-change-signal-return.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 | $0.00030 | $0.00392 |
| Opus 5 | $0.00015 | $0.00196 |
| Sonnet 5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
aggregated-change-signal-return 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.
What it actually says
SKILL: Aggregated Change Signal Return
Domain: extensions-mcp
Trigger: Apply when a headless setup flow can change state through several mechanisms but callers only need one final answer about whether they must refresh downstream registries.
Source Pattern: Distilled from reviewed extension lifecycle and source-reconciliation patterns.
Core Method
Aggregate every state-changing branch inside the headless install flow into one caller-facing signal. Seed registration, marketplace reconciliation, and delisting can each materially change the runtime even if the others do nothing, so the function should accumulate them into a single boolean that tells the caller whether a follow-up refresh is required. This keeps the internal branching detailed while exposing a minimal external contract.
Key Rules
- Initialize the change signal from the earliest state-changing step instead of only from the main reconcile path.
- Fold every later state mutation into the same signal, even if it comes from cleanup or enforcement rather than install.
- Keep the caller contract narrow: one signal that means "refresh downstream state now," not a grab bag of internal counters.
- Update the signal only on genuine state changes so callers do not refresh on no-op runs.
Example Application
If a headless extension bootstrap registers seeds, installs missing registries, and removes delisted plugins, return one extensionsChanged boolean that becomes true if any of those paths modified the effective plugin set. The caller can then refresh command discovery once, regardless of which branch caused the change.
Anti-Patterns (What NOT to do)
- Do not expose only install counts when cleanup or seed registration can also require a downstream refresh.
- Do not make callers reconstruct change state from several independent metrics when the callee already knows the full picture.
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 · 28 lines · 30 tokens per session scan A 6d1fb8c13c85
aggregated-change-signal-return is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 392 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 2026-08-30.
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.