Borrowing it
Nothing to install: this file belongs to BloomBooks/BloomDesktop. 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/BloomBooks/BloomDesktop/master/.claude/skills/run-bloom/SKILL.mdgit clone --depth 1 https://github.com/BloomBooks/BloomDesktopWrote 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/bloombooks/bloomdesktop/run-bloom)<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/run-bloom"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/run-bloom/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/bloombooks/bloomdesktop/run-bloom"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/run-bloom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
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 →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Agent Snooping · line 13 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 83 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 84 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00100 | $0.01787 |
| Opus 5.5 | $0.00040 | $0.00715 |
| Sonnet 5.5 | $0.00020 | $0.00357 |
| Haiku 4.5 | $0.00010 | $0.00179 |
Grade A, and why
run-bloom 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 20d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Bloom (desktop app)
Bloom is a C#/WinForms shell hosting a React UI in WebView2. You drive it through the dev
launcher's control API and CDP. This file is the quick path; reference.md beside it has every
mechanism, rule, and field-verified gotcha, and the driver scripts live in this folder. Paths
are repo-root-relative; commands are bash.
1. Make sure Bloom is running
node .claude/skills/run-bloom/launcherControl.mjs --status --json
# exit 0 → launcher live; status has state, httpPort, cdpPort, vitePort, bloomProcessId
# exit 2 → nobody home (or starting:true = a launch is underway; never start another)
node .claude/skills/run-bloom/launcherControl.mjs --ensure-running --wait-ready --json
--ensure-running handles everything: stale discovery files, a launcher mid-startup (waits
instead of double-launching), an uninitialized worktree (go.mjs runs ./init.sh itself,
phase:"init"), and starting the stack decoupled from your session (an Orca terminal tab when
available, else detached to output/bloom-launcher.log). It starts Bloom with --dont-disturb, so
none of Bloom's windows takes the foreground or the keyboard from the person at the machine (a
Bloom already running keeps whatever it was started with). Never launch ./go.sh tied to your own
shell except when debugging the launcher itself, and never run an already-built Bloom.exe
directly (it is stale).
A cold first build outlasts --wait-ready's default patience: the wait can give up while
--status still says state:"building", and that is not a failure. Pass --timeout-ms 600000,
run the command as a background task and act on its completion; never sleep-poll --status, and
never re-invoke --ensure-running after a timeout without checking --status first.
2. Get a .NET change into Bloom
node .claude/skills/run-bloom/launcherControl.mjs --restart --wait-ready --json
The only way: never ask the human to quit and restart, never kill and relaunch by hand. It
returns the fresh ports. Front-end (.ts/.tsx/.less) edits need no restart; the Vite dev
server pushes them into the running Bloom.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- ai-image-editor-driving.md 8.9 KB
- bloomProcessCommon.mjs 12 KB runs code
- bloomProcessStatus.mjs 8.0 KB runs code
- dismissProblemDialog.mjs 12 KB runs code
- driveAiImageEditor.mjs 11 KB runs code
- killBloomProcess.mjs 8.1 KB runs code
- launcherControl.mjs 21 KB runs code
- reference.md 32 KB
- screenshotBloom.mjs 5.7 KB runs code
- switchWorkspaceTab.mjs 9.5 KB runs code
- webview2Targets.mjs 9.0 KB runs code
- winformsUia.ps1 9.7 KB runs code
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.
- 20d ago Changed · +9 lines 6bb80920a475
- 1mo ago Changed · +4 lines 5cb14cd5a920
- 1mo ago Changed · +7 lines · +34 tokens per session 6b4f7969fee3
- 1mo ago Changed · +2 lines f414af5c3237
- 1mo ago Changed · +8 lines 0937fee4632b
- 2mo ago First seen · 85 lines · 66 tokens per session scan A 0a640b32929c
run-bloom is a skill published in the GitHub repository BloomBooks/BloomDesktop (43 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,787 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 2026-08-30.
Other skills, from other repositories
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.