Boop is a personal agent that people use through iMessage, backed by either the Claude Agent SDK or the local Codex app-server runtime. It provides memory, sub-agents, automations, and integrations such as Gmail, Slack, GitHub, Linear, and Notion.
Borrowing it
Nothing to install: this file belongs to raroque/boop-agent. 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/raroque/boop-agent/main/.agents/skills/upgrade-boop/SKILL.mdgit clone --depth 1 https://github.com/raroque/boop-agentWrote 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/raroque/boop-agent/upgrade-boop)<a href="https://agentmods.dev/skills/raroque/boop-agent/upgrade-boop"><img src="https://agentmods.dev/badge/skills/raroque/boop-agent/upgrade-boop/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/raroque/boop-agent/upgrade-boop"><img src="https://agentmods.dev/badge/skills/raroque/boop-agent/upgrade-boop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 16 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 190 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Privilege Escalation · line 155 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00033 | $0.01923 |
| Opus 5 | $0.00016 | $0.00962 |
| Sonnet 5 | $0.00007 | $0.00385 |
| Haiku 4.5 | $0.00003 | $0.00192 |
Grade A, and why
upgrade-boop 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 10d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
About
Your Boop fork drifts from upstream as you customize it — system prompts tweaked, new automations, tuned memory thresholds, etc. This skill brings upstream changes in without blowing away those edits.
Run /upgrade-boop inside the repo from Codex. This is the supported upgrade path: the agent previews the diff, creates rollback points, performs the merge, resolves conflicts when needed, and runs referenced migration skills.
How it works
Preflight: refuses to touch anything with a dirty working tree. If the upstream remote is missing, adds it (default: https://github.com/raroque/boop-agent.git — the skill will ask).
Backup: creates a timestamped rollback branch + tag before doing anything. Printed at the end so you can git reset --hard back.
Preview: buckets upstream changes into categories so you know what's about to land:
- Core (
server/) — the dispatcher, executor, memory, automations. High conflict risk if you edited your prompts. - Integrations (
server/composio*,server/integrations/) — Composio wiring. - UI (
debug/) — debug dashboard. - Schema (
convex/) — Convex tables + functions. Pushes happen on nextconvex dev. - Scripts / config (
scripts/,package.json,tsconfig.json,.env.example) — env vars + deps might need attention. - Docs (
README.md,ARCHITECTURE.md,INTEGRATIONS.md,CHANGELOG.md).
Choice: you pick merge (one-pass), cherry-pick (specific commits), rebase (linear history), or abort.
Conflict preview: dry-run merge to show which files would conflict before you commit.
Validation: npm install + npm run typecheck after the merge.
Breaking changes: parses the CHANGELOG.md diff for [BREAKING] entries and surfaces each one. Many breaking changes will reference a migration skill (/<skill-name>) — the skill offers to run those for you.
Summary: prints rollback tag, new/upstream HEADs, and any env-var additions from .env.example you should copy into .env.local.
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.
- 10d ago First seen · 193 lines · 33 tokens per session scan A f1ff37fc1967
upgrade-boop is a skill published in the GitHub repository raroque/boop-agent (1,357 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,923 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
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…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.