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 classified-skill-listing-debug-telemetrygit 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/classified-skill-listing-debug-telemetry)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/classified-skill-listing-debug-telemetry"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/classified-skill-listing-debug-telemetry/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/classified-skill-listing-debug-telemetry"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/classified-skill-listing-debug-telemetry.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 | $0.00042 | $0.00418 |
| Opus 5 | $0.00021 | $0.00209 |
| Sonnet 5 | $0.00008 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
classified-skill-listing-debug-telemetry 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 10d 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: Classified Skill Listing Debug Telemetry
Domain: command-surfaces
Trigger: Apply when a listing or announcement pipeline needs debuggable operational signals, but logging the full payload would be noisy, expensive, or sensitive.
Source Pattern: Distilled from reviewed command-surface and listing-control patterns.
Core Method
Emit one compact debug log per listing batch that classifies the batch and summarizes its size. Record the current batch count, whether it is the initial or a dynamic update, and the cumulative sent total after state mutation, but omit the actual payload content. This gives operators enough information to trace listing behavior, verify delta logic, and spot regressions without leaking or duplicating the rendered skill list in logs.
Key Rules
- Log derived counts and batch class, not the rendered listing body or full command set.
- Use the same post-filter batch that will actually be emitted so telemetry matches runtime behavior.
- Include both per-batch and cumulative counts; one without the other makes delta behavior harder to debug.
- Keep the telemetry call close to payload construction so classification and counts cannot drift from what is sent.
Example Application
If a REPL session emits a first skill-listing attachment with seven items, log a line such as "sending 7 skills, initial, 7 total sent" before formatting the payload. When two more skills appear after a plugin reload, emit a second line classified as dynamic with the updated cumulative total, without logging the actual skill names.
Anti-Patterns (What NOT to do)
- Do not log the full listing payload just to debug batch behavior; it bloats logs and may expose irrelevant content.
- Do not emit debug telemetry from the pre-filter command pool; the logged counts must reflect the exact emitted delta.
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.
- 10d ago First seen · 28 lines · 42 tokens per session scan A 57cfa507a98f
classified-skill-listing-debug-telemetry is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 42 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 2026-08-30.
Other skills, from other repositories
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
report
Investigate bugs comprehensively — cascade through trace, capture browser evidence, extract observability data, and prepare or explicitly create a GitHub issue with grounded findings.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
perf
Use when auditing performance in any codebase — cold starts, hot paths, dependency weight, storage query patterns. Assess by default, optimize on request; measure, don't guess, and every number carries the command that produced it.
use-ivygrep
Gather focused local repository context with ivygrep before implementing, debugging, reviewing, or explaining code. Use for coding tasks involving unfamiliar paths, branch changes, stack traces, architectural relationships, callers, dependents, tests, configuration, or documentation. Prefer one bounded context pack…
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.