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 runxhq/runx --skill operations-reviewgit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/operations-review)<a href="https://agentmods.dev/skills/runxhq/runx/operations-review"><img src="https://agentmods.dev/badge/skills/runxhq/runx/operations-review/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/runxhq/runx/operations-review"><img src="https://agentmods.dev/badge/skills/runxhq/runx/operations-review.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 | $0.00048 | $0.03704 |
| Opus 5.5 | $0.00019 | $0.01482 |
| Sonnet 5.5 | $0.00010 | $0.00741 |
| Haiku 4.5 | $0.00005 | $0.00370 |
Grade A, and why
operations-review 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 today.
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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operations Review
Operate a project, workspace, or account from an agent-controlled desk.
This skill is the generic operations desk layer. It turns a state snapshot, an operator objective, and receipt-backed evidence into one safe ops desk packet: what is happening, what needs attention, what can be checked read-only, what requires approval, which governed lane should execute, and how success will be verified.
It is not the authority and it is not a second CLI. It does not replace domain skills from the registry (release, payments, board and thread products, and the like), provider-specific adapter skills, hosted API routes, repository workflows, or deploy commands. It routes to the existing interface with the smallest sufficient context and stops before any consequential act that lacks the right gate.
What this skill does
The default operate runner reviews an already-supplied snapshot. The explicit
operate_from_projection runner can read a bounded product-owned projection
before review. Neither owns the product state or a continuing work lifecycle. Both classify findings,
rank the next action, select the governed lane, name blockers, write the
approval prompt when a human decision is required, and states the
receipt/effect/readback that will prove success.
It is useful before an action and after an action:
- before action, it turns state into proposals and approval requests;
- after action, it checks whether the expected receipt and projection appeared.
The model may diagnose and write the operator rationale. The mutation itself must be a deterministic handoff to an existing skill runner, CLI command, hosted API route, workflow, or provider tool.
When the desk should start from durable state, use operate_from_projection.
That runner reads a projection through the store's projection.read first, then passes the
projection as the dashboard snapshot. The storage provider is still selected by
the logical data_source_ref; ops desk does not know whether state came from
SQLite, Postgres, D1, Redis, or a product API.
What ships with it
15 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.
- fixtures/action-review-awaits-approval.yaml 1.3 KB
- fixtures/composes-in-graph.yaml 737 B
- fixtures/operate-from-sqlite-projection.yaml 3.0 KB
- fixtures/payment-status.yaml 3.6 KB
- fixtures/support/composed.graph 888 B
- mark.svg 482 B
- references/catalog.md 190 B
- references/communications.md 1.5 KB
- references/dashboard.md 2.0 KB
- references/delegation.md 2.4 KB
- references/mark-license.md 3.1 KB
- references/payments.md 2.8 KB
- references/providers.md 1.4 KB
- references/receipts.md 1.2 KB
- run.yaml 14 KB
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.
- today First seen · 361 lines · 48 tokens per session scan A 9d986ad5fcef
operations-review is a skill published in the GitHub repository runxhq/runx (103 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 3,704 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 2026-10-18.
Other skills, from other repositories
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
backlog-capture
Quickly capture product ideas, feature requests, or insights from meetings and conversations. Rapid documentation with smart categorization and deduplication.
queue-handoff
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messages, and interruptions. Covers the hot-potato terminal-turn-rule (active work ends by passing the ball, not by going…