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 LucasSantana-Dev/sharekit --skill ci-watchgit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/lucassantana-dev/sharekit/ci-watch)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/ci-watch"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/ci-watch/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/lucassantana-dev/sharekit/ci-watch"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/ci-watch.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 | $0.00055 | $0.00959 |
| Opus 5.5 | $0.00022 | $0.00384 |
| Sonnet 5.5 | $0.00011 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
ci-watch 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ci-watch
Use for broken checks, flaky tests, or merge-blocking pipeline noise.
Steps
- Identify the active PR or HEAD commit.
- List non-passing checks.
- Separate required failures from advisory noise.
- Inspect the first failing job deeply.
- Name the smallest fix or the exact reason the failure is unrelated.
Output
Return:
- failing job
- first bad signal
- likely cause
- likely owner surface
- smallest viable fix
- whether it blocks shipping now
PR state machine
Read gh pr view N --json mergeable,mergeStateStatus,reviewDecision first, then:
| mergeable / state | Action |
|---|---|
MERGEABLE + CLEAN |
proceed to merge |
MERGEABLE + UNSTABLE |
non-required check failing or pending; poll required-only checks |
MERGEABLE + BEHIND |
gh pr update-branch or local rebase + force-push |
MERGEABLE + BLOCKED |
check reviewDecision and branch protection; if self-PR → enforce_admins toggle pattern |
CONFLICTING + DIRTY |
local rebase first; if git merge-tree reports clean but GH disagrees → webhook desync, close+recreate PR |
UNKNOWN + UNKNOWN |
GitHub still computing — wait 15s, recheck once; if STILL UNKNOWN, try gh pr merge directly (may already be merged) |
Polling with Monitor
For checks that take >1 min to settle, use the Monitor tool with an until-loop instead of busy-waiting:
Monitor command: until s=$(gh pr view N --json statusCheckRollup); \
pend=$(echo "$s" | python3 -c "..."); [ "$pend" = "0" ]; do sleep 15; done
Don't issue a single long sleep — the harness blocks chained sleeps.
Common gotchas
UNKNOWNoften means the PR was already merged in another window. Verify withgh pr view N --json statebefore re-arming a monitor.mergeStateStatus: BLOCKEDwith no failing checks = review or branch protection. Look atrequiredStatusChecks+requiredApprovingReviewCount.BLOCKED+ all green + bot review threads (CodeQL, CodeRabbit, Greptile) = unresolved conversation. Bots are not "another person" — auto-resolve viaresolveReviewThreadGraphQL mutation.- A PR head SHA that disagrees with
git ls-remotefor its branch ref = webhook desync. Close + recreate, don't try to nudge.
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.
- 1mo ago First seen · 84 lines · 55 tokens per session scan A 742920cf2e0b
ci-watch is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 959 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
atmos-lint
Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings. Use when configuring, running, debugging, or documenting Terraform/OpenTofu linting in an Atmos project.
ci-fix-monitor
Codex adapter for monitoring and fixing CI failures on opencode-swarm PRs. Use when diagnosing failed checks, fixing package-check (npm tarball) failures, resolving quality/lint/format errors, fixing macOS cross-platform file I/O failures, or watching a PR until all checks are green.
swarm-ci-monitor
Codex adapter for end-to-end CI monitoring of an already-reviewed PR in opencode-swarm. Use when the user wants the swarm to monitor a reviewed-and-approved PR's CI, research every failure exhaustively, fix end-to-end, iterate until green (max 5 cycles), then merge. Composes ci-fix-monitor for fix recipes.
diagnose-ci-failures
Diagnose failing CI, lint, typecheck, build, or test logs and propose or implement the smallest verified fix.
github-ci-fix
Fix failing PR checks, debug GitHub Actions, or account for CI follow-up rounds and wait for verification.
ci-self-heal
A diagnostic guide for analysing failed continuous-integration checks. Continuous integration, or CI, automatically tests and builds code changes; this guide classifies failures and suggests fixes without editing the code.