Borrowing it
Nothing to install: this file belongs to cardstack/boxel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cardstack/boxel/main/.claude/skills/policy-performance/SKILL.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/policy-performance)<a href="https://agentmods.dev/skills/cardstack/boxel/policy-performance"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/policy-performance/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/cardstack/boxel/policy-performance"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/policy-performance.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 | $0.00299 | $0.02769 |
| Opus 5.5 | $0.00120 | $0.01108 |
| Sonnet 5.5 | $0.00060 | $0.00554 |
| Haiku 4.5 | $0.00030 | $0.00277 |
Grade A, and why
policy-performance 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Policy performance
A realm's policy is consulted only for a caller its ACL declined. For those callers every invocation passes the gate (card-operations/gate.ts), every search composes the policy's query filters (card-operations/policy-query.ts), and the realm keeps a compiled copy of the policy card (RealmPolicyCache in card-operations/policy.ts). Each of those writes one JSON record per event on the boxel:operations channel (card-operations/telemetry.ts). These records are how the cost is measured. For what they say about correctness rather than cost — why a caller was refused, which policy won't compile, which grant admits too much — read operations-diagnosis.
The records
Every line is one JSON object with channel: "boxel:operations" and a kind. The same channel carries kind-less operation-execution records and capability-check records, so filter on kind first.
kind |
one line per | cost fields |
|---|---|---|
policy-decision |
gate decision for a caller the ACL declined (and, for a write left to the lock, the lock's) | evaluationMs, predicateMs, predicates, tier |
policy-search-scope |
realm a search consulted through its policy | evaluationMs |
policy-compile |
read of a realm's policy card by its cache: a compile or a revalidation | durationMs, outcome, rules, grants |
policy-snapshot-read |
evaluation of a predicate annotated snapshot: true (reads the index row, Tier 1/2) |
(count only) |
capability-check |
_capabilities request |
totalMs, pairs |
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.
- 5d ago First seen · 96 lines · 299 tokens per session scan A d93360131ccd
policy-performance is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 299 tokens to every session and 2,769 once invoked, about $0.0012 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 2026-10-21.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.