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 Snowflake-Labs/cocoplus --skill meter-comparegit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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/snowflake-labs/cocoplus/meter-compare)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/meter-compare"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/meter-compare.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00931 |
| Opus 5 | $0.00015 | $0.00465 |
| Sonnet 5 | $0.00006 | $0.00186 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
meter-compare 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill for $meter compare.
Objective
Compare two CocoMeter or harness benchmark result files while respecting the configured optimization objective. The default is correctness-first: accuracy delta is the primary signal and token/cost delta is secondary.
CocoMeter session summaries may include three named cost rows:
execution_cost: functional stage work.coordination_cost: advisor calls, handoff context assembly, artifact transfer, and status sync.landing_cost: reserve-window spend for final evaluation, console update, and handoff.
When [meter] track_acrr = true, session summaries may also include:
acrr_this_session: average Agent Cognitive Redundancy Ratio across completed CocoFlow runs in the session.acrr_runs[]: the last run-level records withcomplexity_tier_estimated,model_tier_configured,model_tier_actual,model_tier_used,model_drift,escalations_taken, andacrr.
When [meter] meter_reconciliation_enabled = true, finalized session summaries may include reconciliation_status, metering_gap_fraction, duplicates_found, model_tier_configured, model_tier_actual, and model_drift. Treat transcript-derived totals as authoritative for billing comparisons when reconciliation_status is gap_corrected.
Treat ACRR as a calibration diagnostic, not an accuracy score. ACRR near 1.0 indicates that the initial complexity tier was sufficient. Consistently high ACRR indicates the task class is being underestimated before dispatch.
Workflow
- Parse
$meter compare <before.json> <after.json>. - Read both files. Accept fields named
accuracy,score,task_accuracy,cost,tokens, orcredits. - Read
cocoplus.toml [meter]:optimization_objective, defaultcorrectness-firstaccuracy_equivalence_band, default0.02cost_first_acknowledged, defaultfalsetrack_acrr, defaulttrue
- Compute accuracy delta before cost delta.
- If objective is
cost-firstbutcost_first_acknowledgedis not true, treat the run as correctness-first and warn. - If both files include ACRR, report ACRR trend after accuracy and before detailed cost rows. A lower ACRR with unchanged accuracy means the harness is better calibrated; a higher ACRR with unchanged accuracy means the run succeeded but over-expanded.
- If either file includes reconciliation or model-drift metadata, report it after ACRR and before cost rows.
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.
- 3d ago First seen · 81 lines · 29 tokens per session scan A b989969b17ee
meter-compare is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 931 once invoked, about $0.0001 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
implement-universal
Harness-agnostic version of /implement. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as agents/software-engineer.md and agents/tester.md instead of being launched as subagents. Resolves the ticket from implementyourself/tasks/, creates an…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
bare-eval
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
testing-e2e
End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
synthesize-verification-report
Aggregate all detected errors and gaps into the final verification report, apply strict accept/reject logic, and produce repair hints when rejected.