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 sd0xdev/sd0x-harness --skill watch-cigit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/watch-ci)<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/watch-ci"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/watch-ci/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/sd0xdev/sd0x-harness/watch-ci"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/watch-ci.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 | $0.00086 | $0.02460 |
| Opus 5.5 | $0.00034 | $0.00984 |
| Sonnet 5.5 | $0.00017 | $0.00492 |
| Haiku 4.5 | $0.00009 | $0.00246 |
Grade A, and why
watch-ci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch CI
Monitor GitHub Actions CI runs for the current HEAD (or a specified SHA) until completion, then report verdict.
Trigger
- Keywords: watch CI, check CI, CI status, monitor build, build status, is CI passing, watch actions, CI result
When NOT to Use
- Pushing code to remote (use
/push-ci) - Creating pull requests (use
/create-pr) - Running local tests (use
/verifyor/precommit)
Workflow
Auto-detect (branch + SHA) → Find matching runs → Quick-check status → Watch or Report → Verdict
Step 1: Resolve Target
Determine which CI runs to monitor. Use arguments if provided, otherwise auto-detect.
BRANCH=${ARG_BRANCH:-$(git rev-parse --abbrev-ref HEAD)}
HEAD_SHA=${ARG_SHA:-$(git rev-parse HEAD)}
TIMEOUT=${ARG_TIMEOUT:-10}
INTERVAL=${ARG_INTERVAL:-30}
If --run-id <id> is specified, skip run discovery and monitor that specific run directly.
Step 2: Find CI Runs
Find runs matching the target SHA on the target branch:
gh run list --branch "$BRANCH" --limit 30 \
--json databaseId,headSha,status,name,url
Note: Use
--limit 30(not 10) to avoid missing target SHA runs on busy branches. Filter results client-side byHEAD_SHA.
Filter results to those matching HEAD_SHA.
Retry logic: If no matching runs found, retry up to 3 times by re-running the gh run list command. The natural processing delay between retries provides sufficient wait time — do not use sleep N (N ≥ 2) as the first command, the harness will block it. All retry commands must start with gh or git to match allowed-tools. CI workflows may take a few seconds to trigger after push.
If still no runs found after retries:
⚠️ No CI run detected for SHA <sha>. Possible causes:
- No workflow configured for this branch
- Path-filtered workflow didn't trigger
- Check: gh run list --branch <branch>
Step 3a: Quick Status Check
Before starting a long-running watch, check if runs are already completed:
gh run view <run-id> --json status,conclusion,name,url
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 · 203 lines · 86 tokens per session scan A 1b4abd4a7a68
watch-ci is a skill published in the GitHub repository sd0xdev/sd0x-harness (194 stars, last pushed 15d ago), licensed MIT. It adds 86 tokens to every session and 2,460 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 2026-09-03.
Other skills, from other repositories
comet-github-ci-triage
A workflow for diagnosing failed GitHub Actions checks on a Comet pull request. GitHub Actions runs automated builds and tests; a pull request is a proposed code change waiting to be reviewed and merged.
building
Use when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns.
cc10x-guide
Answers questions about cc10x itself — what it is, how to install and configure it, how the router, workflows, memory, and hooks operate, and how to troubleshoot. Use this skill when: the user asks ABOUT cc10x — "what is cc10x", "how do I configure cc10x", "why isn't cc10x activating", "how do cc10x workflows work"…
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.
exploration
Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.