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 serac-labs/serac --skill studio-source-controlgit clone --depth 1 https://github.com/serac-labs/seracWrote 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/serac-labs/serac/studio-source-control)<a href="https://agentmods.dev/skills/serac-labs/serac/studio-source-control"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/studio-source-control/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/serac-labs/serac/studio-source-control"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/studio-source-control.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 | $0.00059 | $0.01648 |
| Opus 5.5 | $0.00024 | $0.00659 |
| Sonnet 5.5 | $0.00012 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
studio-source-control 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Studio Source Control
A scoped application can be linked to a git repository, after which its records are committed and pushed
like code. snow_source_control drives that over /api/sn_source_control.
This is not the Fluent toolchain. The fluent-* skills are about building an app from a local SDK
project; this is the platform's own git integration, reached from inside the instance. Both end up in a
repository and they are different routes.
Before it works at all
Source Control fails in ways that look like tool bugs when any of these is missing. Check them first:
- The app is scoped. Global-scope artefacts cannot be linked.
sys_appwith a scope likex_company_module. - The app is linked to a repository. Done once, in Studio (
Source Control → Link to Source Control). Nothing here creates the link. - Credentials exist on the instance. A
sys_repo_credentialrecord holding the repo credential — a PAT for GitHub/GitLab, not a password. Pass its alias ascredentials_aliaswhen the remote needs auth. - The Source Control plugin is active and the instance can reach the remote outbound. On a restricted network that means a MID server, and the failure is a timeout rather than a 401.
Confirm the link before anything else:
await snow_query_table({ table: "sys_app", query: "scope=x_acme_ops",
fields: "sys_id,name,scope,sys_class_name" })
await snow_source_control({ action: "status", app_scope: "x_acme_ops" })
status on an unlinked app is the fastest way to find out you are not where you think you are.
Commit, then push — they are separate
The order is git's, not ServiceNow's, and the tool does not merge the two:
// 1. what changed in the working copy
await snow_source_control({ action: "status", app_scope: "x_acme_ops" })
// 2. commit it locally, with a message
await snow_source_control({ action: "commit", app_scope: "x_acme_ops",
commit_message: "fix: widen the assignment lookup" })
// 3. and only then send it to the remote
await snow_source_control({ action: "push", app_scope: "x_acme_ops", credentials_alias: "acme-github" })
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 · 148 lines · 59 tokens per session scan A 176dd13cb93b
studio-source-control is a skill published in the GitHub repository serac-labs/serac (78 stars, last pushed 6d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,648 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 2026-09-11.
Other skills, from other repositories
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
git
Run git version control commands for repository management. Use when the user asks to check status, view history or diffs, stage and commit changes, manage branches, merge or rebase, work with remotes, stash changes, tag releases, cherry-pick commits, bisect regressions, resolve conflicts, manage worktrees or…
yeet
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (gh).
github-cli
Skill "github-cli" from juan294/cc-rpi, covering github cli, json field discovery, pr check interpretation, or watch existing checks to completion and release vs pr flags.
git-wrapup
Review verified mcp-reporter changes, prepare versioned changelog entries, create logical commits and an annotated local tag. No push or publish.