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 dork-labs/dorkos --skill ci-local-exportgit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/dork-labs/dorkos/ci-local-export)<a href="https://agentmods.dev/skills/dork-labs/dorkos/ci-local-export"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/ci-local-export/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/dork-labs/dorkos/ci-local-export"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/ci-local-export.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 | $0.00067 | $0.00691 |
| Opus 5.5 | $0.00027 | $0.00276 |
| Sonnet 5.5 | $0.00013 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
ci-local-export 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 27d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ci-local-export
The lefthook time-wrap (packages/ci-steward/bin/time-wrap.sh) records a START and an END line for every hook command in $(git rev-parse --git-common-dir)/ci-steward/local-timings.jsonl. That file lives only on this machine, so a GitHub Actions job cannot read it. This job pushes one aggregate per finished day to local/<clone>/YYYY-MM-DD.json on the ci-steward-data branch, where the daily collector turns it into the local-commit and local-push SLOs. It runs at 04:30 UTC, half an hour before the collector.
Run
pnpm ci:local-export
Then report its output in one or two lines: how many days it exported, whether it pushed, and whether it rotated the file. It never needs anything else.
What it does
- Reads the timings file and pairs each START with its END. An END with a signal status (128 + HUP, INT or TERM) is a killed run, and so is a START with no END older than
local.killed_after_secondsinci/config.yaml(the pre-push watchdog's ceiling plus margin); a younger unmatched START might still be running and is left for tomorrow. - Writes each finished day under
local/<clone>/. The clone name is a short digest of this machine and this clone, never the hostname (the branch is public); setCI_STEWARD_CLONEor pass--clone <name>to choose one. - Pushes with fetch, rebase and retry. It never creates the branch: before the collector's first run it says so and pushes nothing.
- Writes a heartbeat,
local/<clone>/exported.json, on every run, so an idle clone (no commits, no pushes) never reads as a stale export. - Rotates the file: lines older than 30 days go, and past 5 MB the oldest half goes. Lines appended while it rewrites are kept.
Approving it
DorkOS finds the schedule: block above and puts this job on the Schedules page as Waiting for approval. It does not run until the operator approves it. Approve it with Approve at Full autonomy: the job runs Bash and git push, and a schedule that arrives in a file is held back to the careful setting, which cannot run either unattended (DOR-2100; docs/guides/task-scheduler.mdx). With plain Approve, every run ends Blocked.
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.
- 27d ago First seen · 36 lines · 67 tokens per session scan A a417f54629fe
ci-local-export is a skill published in the GitHub repository dork-labs/dorkos (10 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 691 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 2026-09-20.
Other skills, from other repositories
github-flow-for-claude-on-web
Complete GitHub workflow for Claude Code on the web. ALL GitHub operations MUST use REST API (never gh CLI). Includes branch naming (claude/-sessionId), push retry logic, PR/issue management via API, and complete workflows. Use for all GitHub interactions in Claude Code web environment.
stacked-pr-merge
Merging a stack of dependent PRs in this repository — a branch cut from another PR's branch rather than from main. Covers the one merge API that is not 403 here, taking the head SHA from the API, and the stale-lineage rebase that produces mass conflicts if you use plain git rebase origin/main. Use when gh pr merge…
vibing-worktree-create
Create a new git-worktree-backed isolated work area for the current vibing.nvim chat via natural language — no separate UI. Use when the user wants to isolate work in its own worktree ("split this into its own worktree", "start this in isolation", "give this its own branch").
vibing-worktree-attach
Attach the current or a new vibing.nvim chat to an already-existing git worktree via natural language — no separate UI. Use when the user wants to switch/attach a chat to an existing worktree ("let's go into the auth-fix worktree", "attach to worktree X", "continue in the feature-y worktree").
vibing-worktree-finish
Remove a git-worktree-backed isolated work area for vibing.nvim chats via natural language — no separate UI. Use when the user wants to clean one up when done ("clean up this worktree", "I'm done with this branch's worktree", "remove the auth-fix worktree").
vibing-worktree-list
List git-worktree-backed isolated work areas for vibing.nvim chats via natural language — no separate UI. Use when the user wants to see what worktrees/branches exist ("what worktrees do I have", "what's in progress", "show me all worktrees").