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 cardstack/boxel --skill indexing-errorsgit 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/indexing-errors)<a href="https://agentmods.dev/skills/cardstack/boxel/indexing-errors"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/indexing-errors/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/indexing-errors"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/indexing-errors.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 | $0.00111 | $0.02436 |
| Opus 5.5 | $0.00044 | $0.00974 |
| Sonnet 5.5 | $0.00022 | $0.00487 |
| Haiku 4.5 | $0.00011 | $0.00244 |
Grade A, and why
indexing-errors 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Realm indexing errors
boxel realm indexing-errors returns four classes of "indexing finding" for a realm:
indexing-error—boxel_indexrows wherehas_error = TRUE. The render or file extract failed and the persistederrorDoc(aSerializedError:message,status,title, optionalstack, optionaldeps) explains why.broken-link—boxel_indexrows wherehas_error = FALSEbut the indexer'srender.metascan persisted a non-emptydiagnostics.brokenLinksarray. The card itself indexes fine; one or morelinksTo/linksToManytargets are dead. Each entry exposesattributes.brokenLinks: BrokenLinkSummary[]—{ fieldName, reference, kind: 'error' | 'not-found' }.frontmatter-error—boxel_indexrows wherehas_error = FALSEbut a markdown file's leading YAML frontmatter wouldn't parse, persisted asdiagnostics.frontmatterParseError. The file indexes body-only, so anything the frontmatter declared (a skill'scommands, itsboxel.kind, etc.) was silently dropped — this finding is the only signal the author gets. Each entry exposesattributes.frontmatterParseError—{ message, line?, column? }.tool-schema-error—boxel_indexrows wherehas_error = FALSEbut one or more of a skill markdown file's frontmatter tools failed index-time schema generation (module wouldn't load, missing export, schema generation threw), persisted asdiagnostics.toolSchemaErrors. The skill indexes with the tools that did enrich; each failed tool won't be callable via the pull model until fixed — this finding is the only indexed signal. Each entry exposesattributes.toolSchemaErrors: ToolSchemaError[]—{ module, name, message }.
Use this skill to triage realm health in one call, without reading the database directly or scraping per-card failures.
When the user asks to...
| Ask | Run |
|---|---|
| "what's failing to index in ?" | boxel realm indexing-errors --realm <realm-url> |
| "which cards have broken links in ?" | boxel realm indexing-errors --realm <realm-url> --json | jq '.data[] | select(.type == "broken-link")' |
| "why did my skill's commands disappear / which files have bad frontmatter?" | boxel realm indexing-errors --realm <realm-url> --json | jq '.data[] | select(.type == "frontmatter-error")' |
| "why isn't my skill's tool callable / which tools failed schema generation?" | boxel realm indexing-errors --realm <realm-url> --json | jq '.data[] | select(.type == "tool-schema-error")' |
| "give me the full payload as JSON" | boxel realm indexing-errors --realm <realm-url> --json |
| "is anything broken in this realm right now?" | boxel realm indexing-errors --realm <realm-url> — exit 0 with "No indexing errors." is the all-clear |
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 · 171 lines · 111 tokens per session scan A 7af86154a000
indexing-errors is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 2,436 once invoked, about $0.0004 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.