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/fold-run/fold/watch-cinpx skills add fold-run/fold --skill watch-cigit clone --depth 1 https://github.com/fold-run/foldWrote 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/fold-run/fold/watch-ci)<a href="https://agentmods.dev/skills/fold-run/fold/watch-ci"><img src="https://agentmods.dev/badge/skills/fold-run/fold/watch-ci.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 | $0.00044 | $0.00508 |
| Opus 5 | $0.00022 | $0.00254 |
| Sonnet 5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
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 5d 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
Watch fold CI
Every push gets watched — pushing and walking away is not done here.
Workflow
-
Find the run:
gh run list -L 3— match the head SHA to what was just pushed (git rev-parse HEAD). Tag pushes triggerrelease.yml(goreleaser) in addition to CI; watch both. -
Watch in the background:
gh run watch <run-id> --exit-statusas a background Bash task, then continue or wait. Report the conclusion when it lands — pass or fail, never silently. -
On failure, fetch the failing job's log (
gh run view <run-id> --log-failed) and triage by job:CI job Local equivalent Usual cause gofmt / tidy make fmt-check/make tidy-checkforgot make fmtorgo mod tidyvet / build / lint make vet/make build/make lintreproduces locally; fix and re-run race tests make racereal concurrency bug — never sleeps or -raceremovalgovulncheck make vulnnew advisory; may be unrelated to the diff — check the CVE before touching deps bench gate make benchhot-path work; use /perf. Compare BENCH_RESULT vs recent green runs before calling flakeconformance make conformancegateway stopped being invisible, or upstream drift; use /conformancehelm make helm-checkchart/values drift -
Reproduce locally before pushing a fix — CI is the verifier, not the debugger. Fix commits follow the same per-step approval as any other commit.
A scheduled drift workflow also runs conformance against unpinned
upstream (main/@latest); a red drift run signals upstream movement,
not a broken merge — handle via /conformance pin-bump, deliberately.
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.
- 5d ago First seen · 38 lines · 44 tokens per session scan A 5dbf9130c6aa
watch-ci is a skill published in the GitHub repository fold-run/fold (1 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 508 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
console
Navigate and interact with the ThunderID Console UI. Use when exploring the ThunderID admin console, testing UI changes, creating users/applications/roles, or debugging the frontend.
go
Use for Go changes in Neva: authoring, refactoring, debugging, or review.
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
config-loader-helper
Diagnose configuration-related failures, enumerate required env vars, and guide safe local test setup (no secrets).
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
fix-suggester
Diagnose failures and propose minimal, test-backed fixes with verification and rollback instructions.