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-reconcilegit 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-reconcile)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/meter-reconcile"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/meter-reconcile/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/snowflake-labs/cocoplus/meter-reconcile"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/meter-reconcile.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 | $0.00029 | $0.00975 |
| Opus 5.5 | $0.00012 | $0.00390 |
| Sonnet 5.5 | $0.00006 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
meter-reconcile 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your objective is to reconcile CocoMeter session totals against an authoritative JSONL transcript using only named transcript fields.
Inputs
Accept either direct invocation arguments or a queued request from .cocoplus/v2-runtime-requests.jsonl:
transcript_pathsession_fileoutthreshold(default0.05)session_ididempotency_key- optional
operation: "adapter-canary"for migration self-tests
Idempotency
Use idempotency_key when supplied. Otherwise derive it from session_id, transcript_path, session_file, and out. If .cocoplus/v2-runtime-settlements.jsonl already contains state: "completed" for the key and out exists, report the existing artifact path and stop.
Do not infer token totals from prose. Only named usage fields from the transcript adapter and numeric runtime meter fields may contribute to totals.
Transcript Adapter Rules
Read JSONL one line at a time. For each valid JSON object, preserve only named fields needed for metering:
id,message_id,parent_idtimestamptype,role,event,kindmodel,model_tier,actual_modelusage,tokens,input_tokens,output_tokens,cache_read_input,cache_write_input
Unknown fields are ignored. Malformed lines produce kind: "other" adapter records and never abort reconciliation.
Deduplicate assistant messages by message_id when present; otherwise use a stable fingerprint of role, timestamp, model, and usage fields.
Reconciliation
- Read
session_fileif present and capture runtime token totals. - Read the transcript through the adapter rules above.
- Sum transcript-derived token totals from assistant/tool usage records.
- Compute
gap_fraction = abs(runtime_tokens - transcript_tokens) / max(runtime_tokens, transcript_tokens, 1). - Mark
reconciliation_statusas:matchedwhengap_fraction <= thresholdgapwhen above thresholdtranscript_onlywhen runtime file is absent but transcript has usagenot_runwhen neither source has usage
- Preserve configured and actual model tier when available. Set
model_drift = truewhen both exist and differ.
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 · 103 lines · 29 tokens per session scan A 2859ef8b4137
meter-reconcile is a skill published in the GitHub repository Snowflake-Labs/cocoplus (726 stars, last pushed 20d ago), licensed MIT. It adds 29 tokens to every session and 975 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
resolve-publish
Commit the validated fix and follow local-only, workflow-owned, or direct PR publication.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
resolve-review-pr
Review an existing fix PR using the audited repro and full diff, preserving branch and approval rules.
resolve-inputs
Select the Resolve mode, recover its input, check the workspace, and discover existing fixes.
resolve-investigate
Verify the reported path, cause, and historical intent before choosing a fix.
resolve-repro-audit
Audit a recovered repro patch, assertions, and behavioral baseline before authoring or reviewing.