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/nightly-triage/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/nightly-triage)<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/nightly-triage"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/nightly-triage/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/nightly-triage"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/nightly-triage.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 | $0.00115 | $0.01807 |
| Opus 5.5 | $0.00046 | $0.00723 |
| Sonnet 5.5 | $0.00023 | $0.00361 |
| Haiku 4.5 | $0.00012 | $0.00181 |
Grade C, and why
nightly-triage scanned grade C with 1 finding 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`rm -rf` from Git Bash. How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nightly triage
docs/nightly-failures/README.md is the high-level place where everyone can see which nightly
failures have already been looked at and where each one stands. This skill brings it up to
date. It is triage, not investigation: find out what failed and whether we already know about
it, take a first look, and record that. Do not chase root causes, write fixes, or gather
in-depth details here. That work belongs on a YouTrack card and/or a branch, and the doc just
links to it.
1. Find the runs to look at
Read the doc's Last updated line. Every nightly run after that date is in scope:
gh run list --repo BloomBooks/BloomDesktop --workflow nightly.yml --limit 10 --json databaseId,createdAt,conclusion,headSha
If there are none, say so and stop.
2. For each failed run, name what failed
gh run view <id> --repo BloomBooks/BloomDesktop --json jobs # failed jobs and steps
gh run view <id> --repo BloomBooks/BloomDesktop --log-failed # the failing step's log
The log is large, so filter it:
- The run's summary lines (
* ✅/* ❌) give each suite's counts. - Drop
[WebServer]lines, which are noise from the component tests. - Playwright failures start at
1) <spec>:<line> › <title>. The 40 lines after that give the error and the source line. - C# failures show as
Failed <TestName>.
Ignore errors from passing suites, such as AggregateError stacks in the vitest output.
3. Classify each failure against the doc
- Seen again: the same test failing the same way as an existing entry. Add the date to that entry's Failed line. If its fix was supposed to cover this, say that it did not.
- Known test, new symptom: an existing entry's test failing in a different way. Add a line to that entry. Make it a new entry only if the cause is clearly different.
- New: not in the doc. Add a short entry: the date, the test and its assertion, and what a first look shows, labelled as a first look. Say plainly what is not yet known.
- Fixed: an entry whose fix has landed, where the nightly has since passed on it. Remove the entry. Its history lives in git and on the card.
What ships with it
1 file 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.
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.
- today Changed · +2 lines b00227f4d9e1
- 2d ago Changed · +5 lines 3151b7cdf8bc
- 20d ago Changed · +33 lines · +9 tokens per session de74a4824194
- 22d ago Changed · +6 lines fec1182c80a8
- 27d ago First seen · 89 lines · 106 tokens per session scan C fecadc780507
nightly-triage is a skill published in the GitHub repository BloomBooks/BloomDesktop (43 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 1,807 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
managing-github-actions-secrets
Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API token, package registry credential, deploy key, or any value referenced via ${{ secrets. }} in .github/workflows/.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
deployment-engineer
Expert deployment engineer specializing in modern CI/CD pipelines, GitOps workflows, and advanced deployment automation. Masters GitHub Actions, ArgoCD/Flux, progressive delivery, container security, and platform engineering. Handles zero-downtime deployments, security scanning, and developer experience optimization.…