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 QuantumByteOSS/quantumbyte --skill build-recoverygit clone --depth 1 https://github.com/QuantumByteOSS/quantumbyteWrote 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/quantumbyteoss/quantumbyte/build-recovery)<a href="https://agentmods.dev/skills/quantumbyteoss/quantumbyte/build-recovery"><img src="https://agentmods.dev/badge/skills/quantumbyteoss/quantumbyte/build-recovery/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/quantumbyteoss/quantumbyte/build-recovery"><img src="https://agentmods.dev/badge/skills/quantumbyteoss/quantumbyte/build-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.00384 |
| Opus 5.5 | $0.00027 | $0.00154 |
| Sonnet 5.5 | $0.00013 | $0.00077 |
| Haiku 4.5 | $0.00007 | $0.00038 |
Grade A, and why
build-recovery 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 1mo 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.
What it actually says
Build-recovery — wait management + failure
The build is the moment the user shifts from evaluating to delighted-or-disappointed. A silent wait or a generic error is where the "it's actually building" belief dies.
While it runs (wait management)
Narrate the next concrete piece coming online — short, present-tense, plural: "wiring the booking calendar… setting up reminders… deploying." Never show "no active activity" or an opaque spinner during the most exciting moment. Tie the narration to their app's real pieces, not generic build steps.
When it fails
A generic "something went wrong, try again" is a belief-erosion event. An honest, specific narration is a belief-reinforcement event — a system that sees its own failure and fixes it is the strongest trust signal there is.
- Name it with the cause if you have it: "the database setup hit a configuration edge case." If you don't: "the build stopped partway — I'm not sure why yet, here's what I can try." Never blame the user.
- Offer the real paths, matched to the cause:
- transient → simple retry: rebuild directly.
- scope/spec issue → retry with refined inputs (back to naming/scope, then rebuild).
- structural mismatch revealed → this may actually be a disqualification; route there.
- Keep the user's momentum: one short honest line, one clear next move, no doc-length apology.
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.
- 1mo ago First seen · 24 lines · 67 tokens per session scan A d089bf70e96f
build-recovery is a skill published in the GitHub repository QuantumByteOSS/quantumbyte (294 stars, last pushed 2d ago), licensed Apache-2.0. It adds 67 tokens to every session and 384 once invoked, about $0.0003 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
factory-triage
Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage.
understand-issue
Investigate a GitHub issue or reported bug the way a seasoned maintainer would — form an independent model before reading the thread's theories, trace the mechanism and history, verify the diagnosis, and return a concise briefing with a verdict and fix direction. Use for triage, root-cause analysis, or…
triage-issue
First-contact triage for a GitHub issue.
gh-bulk-issues
Orchestrate parallel Mastra Code headless instances to debug and fix multiple GitHub issues simultaneously.
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…