Borrowing it
Nothing to install: this file belongs to fulminate-io/knowledge-mcp. 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/fulminate-io/knowledge-mcp/main/.claude/skills/price-an-operation/SKILL.mdgit clone --depth 1 https://github.com/fulminate-io/knowledge-mcpWrote 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/fulminate-io/knowledge-mcp/price-an-operation)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/price-an-operation"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/price-an-operation/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/fulminate-io/knowledge-mcp/price-an-operation"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/price-an-operation.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 | $0.00060 | $0.00543 |
| Opus 5 | $0.00030 | $0.00271 |
| Sonnet 5 | $0.00012 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
price-an-operation 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRICE-AN-OPERATION — wall-clock is the orchestrator's to spend
Only the orchestrator can see whether an operation is serial on a lane's critical path — a subordinate prices its own step, never the pipeline. Every verification-scope ruling is priced BEFORE issue; every long-running dispatch carries a time expectation; every brief carries the standing rule that any single operation projected over ~15 minutes is named before it runs. "More verification" is never free — and the failure is seductive after a run of scope-too-narrow corrections: when "wider" was the fix five times, the sixth widening gets approved unpriced. That is the moment to price it.
The marginal-value test
Hours-scale work needs a written marginal-value sentence: what does this buy that a cheaper instrument does not? No sentence → the work does not run. Common case: whole-package suites already running as boundary gates subsume most of a per-criterion sweep over an untouched sibling surface — the narrow form plus a STATED non-coverage sentence beats an unbounded re-run. Hours-scale trades go to the USER with the price attached.
The tell: writing "budget the N hours" in a dispatch — a cost estimate processed as logistics instead of as a decision input. A duration in a subordinate's report IS a decision input. Test plans mandating long execution carry per-test time estimates and a stated total.
Hard-stop mechanics
When the user orders running work halted, a mailbox message is NOT a stop. Stop the task (kill it), verify no orphaned processes survive, then instruct on resume with the redirect as the first thing read. Preserve partial results — evidence already paid for is kept.
Gate state is a timestamped observation
A criterion's measured state is an observation with a timestamp, not a property — trees move under long-running lanes. Before publishing any gate-status expectation list, re-measure against the CURRENT tree in the same act. A stale red sends an implementer after finished work and erodes the list's authority.
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 · 50 lines · 60 tokens per session scan A 6d2041018a6d
price-an-operation is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 543 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.