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 subagent-metrics-bridginggit 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/subagent-metrics-bridging)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/subagent-metrics-bridging"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/subagent-metrics-bridging/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/subagent-metrics-bridging"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/subagent-metrics-bridging.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 | $0.00463 |
| Opus 5 | $0.00015 | $0.00231 |
| Sonnet 5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
subagent-metrics-bridging 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Subagent Metrics Bridging
Domain: metrics-bridging Trigger: Use when an async subagent loop needs to feed its token/tool-use counts, progress, and completion status back into the host task/analytics stack. Source Pattern: Distilled from reviewed async subagent lifecycle, task-progress, and analytics bridge implementations.
Core Method
Drive the async child-agent lifecycle through one progress bridge that feeds task UI, analytics, and notifications from the same stream. As messages arrive, update visible progress, token counts, and the last-active tool so the host can show meaningful live state. When the stream finishes, finalize the result once, record analytics from that finalized snapshot, and then emit completion notifications or warnings. Heavy post-processing should happen after the task is already marked complete so diagnostics do not block the visible lifecycle.
Key Rules
- Move the visible task status to completed or terminated before running expensive diagnostics or cleanup.
- Derive progress, token counts, and “last tool used” from one shared tracker instead of recomputing them in multiple places.
- Finalize the child-agent result once and use that same finalized snapshot for analytics, notifications, and partial-result handling.
- On aborts or kills, still emit a clean closing notification so the parent task can resolve deterministically.
- Clear agent-specific transient state after every outcome so later runs do not inherit stale progress or artifacts.
Example Application
When adding a new background worker that prefetches repo data for the user, follow this pattern to link its stream to the task UI/notification system and guarantee the analytics pipeline records its token tally even if it aborts midflight.
Anti-Patterns (What NOT to do)
- Don’t log the completion event before the agent result is finalized—duplicated token counts appear if you emit analytics prior to
finalizeAgentTool. - Don’t rely on the final assistant message to always contain text; fallback logic exists inside
finalizeAgentToolto pull the last text block, so duplicating that logic invites bugs.
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 · 29 lines · 30 tokens per session scan A 161e5785b9ee
subagent-metrics-bridging 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 463 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.