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 agentmods add skills/theonedev/tod/fix-failed-buildnpx skills add theonedev/tod --skill fix-failed-buildgit clone --depth 1 https://github.com/theonedev/todWrote 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/theonedev/tod/fix-failed-build)<a href="https://agentmods.dev/skills/theonedev/tod/fix-failed-build"><img src="https://agentmods.dev/badge/skills/theonedev/tod/fix-failed-build.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00884 |
| Opus 5 | $0.00013 | $0.00442 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
fix-failed-build 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 6d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix a failed OneDev build
Inspect the failed build from the user's prompt and implement the fix in the current checkout.
Prerequisites
todis installed and configured.- The current repository belongs to the same OneDev project as the failed build.
- The current checkout is on a branch.
Stop on error
Run the workflow sequentially. On any unrecoverable command failure, missing required output, or failed precondition, report the command and error and stop. Do not continue the workflow.
Workflow
Given a required <build-reference> from the user prompt (e.g. 123, #123,
myproject#123, or PROJ-123):
-
Resolve the build reference. Use the
<build-reference>from the user prompt. If the prompt does not provide a build reference, stop and ask for the failed build reference. -
Verify the checkout context. Do not prepare or switch checkouts.
Confirm that the current checkout is on a branch:
git symbolic-ref --short HEADIf the command fails or reports a detached HEAD, stop and report that the workflow requires a branch checkout.
Confirm the current project:
tod project currentSave the output as
<current-project>. -
Gather and examine build evidence. Run:
tod build get <build-reference> tod build get-log <build-reference>Read the build detail and log content carefully to identify the failure. Verify that the build belongs to
<current-project>using the project field in the build detail when present. If the build detail indicates a different project, stop and report the mismatch. -
Assess and fix the failure.
- If the log contains a statement like
Dependency build is required to be successful but failed: <dependency-build-reference>, get the dependency build detail. If the dependency build is cancelled, do not investigate or fix it; report that the relevant dependency build was cancelled. If its commit hash is the same as the current build, investigate or fix the dependency build failure instead; repeat this process for same-commit dependency build failures. If the dependency build's commit hash differs from the current build, conclude that the current build failure is caused by this dependency build. - If the log contains a statement like
[<report-name>]: found problems with severity <severity-level> or higher, fetch the referenced problems report:
Problems may point to workspace files, 1-based line ranges, or non-workspace artifacts used by the project.tod build get-code-problems <build-reference> <report-name> <severity-level> - If the log contains
[<report-name>]: <count> not passed test cases, inspect the report and any relevant artifacts it references:tod build get-unit-test-report <build-reference> <report-name> tod build get-unit-test-report <build-reference> <report-name> --artifact <artifact-path> > <output-file> - Inspect referenced workspace files as necessary. Inspect
.onedev-buildspec.ymlwhen job configuration may be involved, and run below command to get its schema if you need to modify it:tod build get-spec-schema - If useful, inspect changes since the previous successful build:
tod build get-changes-since-success <build-reference>
- If the log contains a statement like
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.
- 6d ago First seen · 105 lines · 25 tokens per session scan A 2765962c5d60
fix-failed-build is a skill published in the GitHub repository theonedev/tod (14 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 884 once invoked, about $0.0001 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
Orchestrates Volcengine Cloud Detect (云拨测) false-alarm reduction for failing periodic-task dial points. Use for scheduled task scans, retrying failed nodes, control-testing node health, distinguishing real target outages from broken dial points, and suggesting same-type LastMile/IDC/Private replacement nodes. Runs the…