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/pr-privacy/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/pr-privacy)<a href="https://agentmods.dev/skills/cardstack/boxel/pr-privacy"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/pr-privacy/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/pr-privacy"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/pr-privacy.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 | $0.00235 | $0.01710 |
| Opus 5.5 | $0.00094 | $0.00684 |
| Sonnet 5.5 | $0.00047 | $0.00342 |
| Haiku 4.5 | $0.00023 | $0.00171 |
Grade A, and why
pr-privacy 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Privacy: Don't Leak User Data into Public GitHub Surfaces
The boxel repo is open source. Anything that lands on github.com/cardstack/boxel — PR titles, descriptions, review comments, review replies, issue comments on PRs, commit messages, and committed files — is public, permanent, and indexed by search engines. Quoting raw data observed in production or staging into any of those surfaces leaks user information.
Linear is the right home for unredacted detail. Link to a Linear ticket from the PR and put concrete identifiers there.
What counts as user data
Treat any of the following as user data that must be redacted before it touches a public GitHub surface:
- Realm URLs and slugs. A realm URL looks like
<username>/<realm-slug>/. The first path segment is a real Matrix username; the second is a realm name the user chose. Both identify the user. Example shape (do not use real values):<username>/<realm-slug>/. - Card paths under a user realm. Anything past the realm root in a user realm — directory names, card filenames, UUIDs in card filenames, embedded field type names visible in the path. These often reflect what the user is working on.
- User-authored content. Card titles, descriptions, body text, field values quoted from a card document.
- Matrix handles, room IDs that map to user DMs, and email addresses.
- Account IDs that map to a specific person, including Matrix user IDs (
@handle:matrix.boxel.ai). - Captures that incidentally show any of the above in the address bar, breadcrumbs, sidebar, or card body.
What is OK to keep verbatim
- Job IDs and other opaque integers that don't map to a person (
job 209668, internal queue IDs). - System realms that ship publicly — base realm, skills realm, catalog realm, experiments realm. Their slugs are part of the platform.
- Infra identifiers — ECS task names, CloudWatch log group names, RDS instance names, EFS paths like
/persistent/. - Synthesized or generic examples —
example-user/example-realm/example-card.json,placeholder-user/test-realm/sample.json. Pick names that read as obviously synthetic — avoid common first names (alice,bob,chris) since those can collide with real Matrix handles. - Numbers in aggregate — "3 affected cards across 3 user realms", "p95 latency 800ms", row counts, byte sizes.
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 · 86 lines · 235 tokens per session scan A 28f5e14879ab
pr-privacy is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 235 tokens to every session and 1,710 once invoked, about $0.0009 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…