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 Jarroslav/agentic-os --skill mr-watchgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/mr-watch)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/mr-watch"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/mr-watch.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 | $0.00149 | $0.01816 |
| Opus 5 | $0.00075 | $0.00908 |
| Sonnet 5 | $0.00030 | $0.00363 |
| Haiku 4.5 | $0.00015 | $0.00182 |
Grade A, and why
mr-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 8d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mr-watch
Autonomous post-creation babysitter for a single open merge/pull request. Poll the request, diagnose merge blockers, apply the minimal fix, push, and repeat until a terminal state. The MR/PR must already exist — this skill never opens one.
Escalate, don't guess. Deeply tangled conflicts, unknown CI failures, and persistently stuck requests hand back to the user rather than churn.
When to invoke
- User asks to watch, monitor, or keep an eye on an open MR/PR.
mr-submit(or any request-opening skill) hands off the URL it just created.
Inputs
Accept the request reference in any of these forms and extract project path + request ID:
| Form | Example |
|---|---|
| Full URL (any VCS) | https://.../merge_requests/123 |
| Short form | !123 (GitLab-style) or #123 (GitHub-style) |
| Bare number | 123 when the repo is inferable from cwd |
Adapter contract
All platform I/O is indirected — never call a platform CLI directly.
- Read the adapter from
.agentic/guides/project.md, section## Review Adapter. Use the declared adapter only when its status isconfigured. - The operation contract lives in
references/mr-adapters.md. Read it to learn how each named operation maps onto the configured adapter (CLI, MCP server, or custom command).
Named operations you call by name:
| Operation | Returns / does |
|---|---|
| state | request lifecycle: merged / closed / open |
| ci-status | pipeline status: running/pending / failed / passed / none |
| discussions | open threads, with IDs |
| comment | post a reply on a thread |
| target-branch | the request's target branch |
Loop state
Carry these variables across iterations:
| Variable | Purpose |
|---|---|
last_pipeline_id |
most recent pipeline seen |
last_seen_discussion_ids |
threads already triaged |
iteration_count |
loops elapsed |
consecutive_same_failure_count |
same job failing back-to-back after a fix |
Operating loop
What ships with it
2 files 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.
- 8d ago First seen · 201 lines · 149 tokens per session scan A acfe11d2fe5e
mr-watch is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 149 tokens to every session and 1,816 once invoked, about $0.0007 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…