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 DmitriyYukhanov/claude-plugins --skill rungit clone --depth 1 https://github.com/DmitriyYukhanov/claude-pluginsWrote 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/dmitriyyukhanov/claude-plugins/run)<a href="https://agentmods.dev/skills/dmitriyyukhanov/claude-plugins/run"><img src="https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/run/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/dmitriyyukhanov/claude-plugins/run"><img src="https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/run.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 | $0.00138 | $0.04791 |
| Opus 5.5 | $0.00055 | $0.01916 |
| Sonnet 5.5 | $0.00028 | $0.00958 |
| Haiku 4.5 | $0.00014 | $0.00479 |
Grade A, and why
run 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 12d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
issue-to-pr — issue → merge-ready PR pipeline
Ten steps from an issue to a merged PR: the gates block, the depth between them scales to the
tier. Use the current host's tools following R/companions.md; the workflow is shared across
Claude Code and Codex. Resolve S/ to ../../scripts/ relative to this installed SKILL.md's
directory, and R/ to its references/. Use absolute, quoted paths in shell calls, never paths
relative to the project or a plugin environment variable. Run scripts with Bash (Git Bash on
Windows), keeping the working directory on the checkout named by the step. One todo per step.
A script prints KEY=value lines. Exit 2 is a stop: STOP_REASON on stdout, the
instruction on stderr — do what it says, report any PUSH_ERROR, MERGE_ERROR or DIRTY_FILES
verbatim, never work around it, and the same stop a third time is a livelock: hand back. Exit
4 means the call itself was wrong: fix the call and re-run. A red gate exits 1, with the
gate's own code in GATE_<NAME>_EXIT.
Hard rules (never violate)
- Merge is gated on explicit in-session approval, runs ONLY in the main session, via
S/finish.sh merge— never a baregh pr merge, never--admin, never on the turn the PR opens, except a headless self-merge, which happens on the report's turn. Force-push only with--force-with-lease. Under--headlessthe go-ahead is the owner replymerge, or the--auto-mergepolicy throughS/finish.sh merge --auto; a run on an issue that already stopped once never self-merges (R/headless.md). - Ask contract: three moments,
--grillreshapes the first (R/judgment.md) — (1) Step 3: ONE batched question if the ledger has open items, or the grill in its place, (2) the merge gate, (3) a hard stop. Decide everything else yourself and log it, and never ask what a script or the code can answer. - Stage and commit through
S/stage.shwith explicit paths; nevergit add -A/.or a diff piped intoxargs git add. The script audits the index immediately before committing. Use the host's file-editing tools for multi-line code. Give PR and issue bodies toghwith--body-file, not interpolated shell strings. - Keep every generated plan, ledger, draft body and resume note under
RUN_DIRfrom Step 1, including files written by companions. Before an owned branch exists, use a unique OS-temp directory (mktemp -d) and retain its absolute path for resume. Never write early notes into the checkout or a sharedrun-maindirectory. - Inspect tracked-state candidates reported by
S/state.sh. Preserve project configuration and unrelated files. Report generated files and offergit rm --cached -- <exact paths>after approval; never delete them or rewrite history. Exclude confirmed generated paths from review inputs with Git pathspecs, even if tracked, and never stage them. Keep config changes in review. - Evidence before assertion: no "green/passing" without the command output; look up any claim
about the world outside this repo before building on it, ledgered either way (
R/judgment.md). - Humanize all human-facing text (report, PR body, UI strings > 1–2 words) at every tier, using the companion or its fallback — not code, logs or commit subjects.
What ships with it
5 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.
- 12d ago Changed · +1 lines c30a593a12ba
- 16d ago Changed · +7 lines b71b1d76c02e
- 18d ago Changed · +19 lines 36726f459f5e
- 19d ago Changed · +13 lines f3eeb1f4bd6f
- 22d ago Changed · +4 lines 63e00225f283
- 24d ago Changed · +11 lines 3971d8a27afb
- 28d ago Changed 8a7730de6a7a
- 1mo ago Changed · +10 lines 4664074c0655
- 1mo ago Changed · +4 lines 0ccdaaaa7ab6
- 1mo ago First seen · 175 lines · 138 tokens per session scan A eb9516106ce3
run is a skill published in the GitHub repository DmitriyYukhanov/claude-plugins (8 stars, last pushed 13d ago), licensed MIT. It adds 138 tokens to every session and 4,791 once invoked, about $0.0006 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
stale-proposals
Audit this repository's local proposal queue for stale entries: proposals still marked proposed, deferred, or accepted even though the work already shipped, plus old proposals whose subject has become inert. Reconcile proposals against plugin changelogs and first-parent Git history, automatically resolve only…
glab
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
apex-status
CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done", or at the start of a work session.
github-activity
Report what happened across GitHub repositories over a time window, read only. Invoke when the user asks what merged, which issues were opened or closed, or what moved between milestones since a date or since the last report, across one or more repositories.
implement-issue
Turn one labelled GitHub issue into one reviewed pull request, or stop with a stated reason. Use for every factory run; the message is a link to the issue.
burn-down-github-issues
Run an unattended burndown of a GitHub issue backlog as cards on a per-operator GitHub Projects board whose lanes are an explicit state machine: appraise and size the inbox, carve what is over the ceiling, fix the ready ones in parallel git worktrees, prove each fix on a draft pull request, have an isolated…