Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.agents/skills/report-to-the-operator/SKILL.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/bredmond1019/claude-sdk-rs/report-to-the-operator)<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/report-to-the-operator"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/report-to-the-operator/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/bredmond1019/claude-sdk-rs/report-to-the-operator"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/report-to-the-operator.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 | $0.00093 | $0.01360 |
| Opus 5.5 | $0.00037 | $0.00544 |
| Sonnet 5.5 | $0.00019 | $0.00272 |
| Haiku 4.5 | $0.00009 | $0.00136 |
Grade A, and why
report-to-the-operator 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 11d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reporting to the operator
The operator runs several agent sessions at once and scans them. Your reply is not a document — it is a status line they read in a few seconds before deciding whether to intervene. Everything durable already goes to disk, because the commands require it. The reply's job is to say what happened and whether it needs them. Nothing else.
The hard contract lives in CLAUDE.md. This skill is the reasoning, the full cut-list, and the
examples.
The shape
- First line = the outcome. What happened, and whether it needs them. No preamble, no restating the request.
- Then the specifics. Bullets, one line each, max ~6. Facts, not narration.
- Last line = the ask, if there is one. One question, answerable in a word.
Ceiling: 10 lines for a normal turn, 20 for an end-of-run report.
The ceiling is not a style preference. Ten lines x six sessions is a screenful; forty lines x six sessions is a reading session the operator did not agree to.
What to cut, in order of how much it costs
| Cut | Why |
|---|---|
| Reasoning narration — how you got there, what you considered, what you almost did | The transcript already holds the steps. Report conclusions. |
| Restating a file you just wrote | Link the path. The operator can open it. Two copies drift. |
| Justifying decisions that worked | Explain only what was non-obvious or what they might reverse. |
| Unasked-for next steps, roadmaps, option menus | They decide what is next. Offer one, if any. |
| Self-assessment and stage direction | "the finding that reframes everything", "worth your attention", praise, hedging, apology. |
| Tables or headings under ~4 rows | A sentence is faster to read than a table with two rows. |
| Preamble — "I'll start by...", "Let me..." | The tool calls already showed that. |
What always earns its space
- Failures and blocks — first, plainly, with the real error text. Never soften, never bury below good news.
- Anything that did not match what was asked.
- Assumptions the operator might reject, and decisions that need their call.
- Security, data-loss, or money implications.
- Exact identifiers where the identifier IS the content —
sdlc-task.js:1481, a commit SHA, an error code. Never a paragraph describing what a one-line reference would say.
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.
- 11d ago First seen · 136 lines · 93 tokens per session scan A 36c26914a4a0
report-to-the-operator is a skill published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,360 once invoked, about $0.0004 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 2026-10-26.
report-to-the-operator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| report-to-the-operatorbredmond1019/claude-sdk-rs | Skill | 23 | 1mo ago | Apache-2.0 | A | 93 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |