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 agentmods add skills/everywan-dev/claude-code-engineering/know-what-a-change-costsnpx skills add everywan-dev/claude-code-engineering --skill know-what-a-change-costsgit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWrote 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/everywan-dev/claude-code-engineering/know-what-a-change-costs)<a href="https://agentmods.dev/skills/everywan-dev/claude-code-engineering/know-what-a-change-costs"><img src="https://agentmods.dev/badge/skills/everywan-dev/claude-code-engineering/know-what-a-change-costs.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 | $0.00052 | $0.01065 |
| Opus 5 | $0.00026 | $0.00532 |
| Sonnet 5 | $0.00010 | $0.00213 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
know-what-a-change-costs 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 6d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Know what a change costs
A change that runs once has a price you can ignore. A change that runs on every request, every commit or every hour has a price that compounds, and nobody notices until the invoice or the quota arrives.
The failure is rarely a big expensive decision. It is a small one multiplied by a frequency nobody wrote down.
🔴 Cost is a property of the change, and it is knowable before you ship. Frequency × unit cost. Both numbers are usually available in under a minute, and almost nobody looks them up.
When to use this
- Adding anything that runs on a schedule, per request, or per commit
- Putting a model call inside a loop
- Adding a query to a hot path
- Choosing between a fast/expensive and a slow/cheap option
- Anything with retries — the interesting number is the retry cost
- After a bill or a quota surprises you
The procedure
1. Write down the frequency, explicitly. Per commit, per user action, per hour, per item in a list that grows. This is the number that gets skipped, and it is the one that decides everything.
2. Multiply by the unit cost. Tokens, queries, requests, seconds of compute, gigabytes egressed. An order of magnitude is enough; you are looking for surprises, not accounting.
3. Then compute the failure cost, which is the one that bites. Retries, back-off loops, a job that reruns because the previous one did not record success, a queue that reprocesses from the start. The expensive scenario is almost never the happy path. Ask what this costs on the worst day, not the average one.
4. Check the ceiling as well as the price. Quotas, rate limits and weekly caps fail differently from money: they stop the work. A cost you can pay is a budget problem; a limit you hit is an outage.
5. Spend where being wrong is expensive; save everywhere else. This is the same rule the validation router uses, and it is the whole of cost discipline in one line. The large model on a security review is cheap insurance. The large model on a changelog entry is waste, three times a day, forever.
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.
- 6d ago First seen · 99 lines · 52 tokens per session scan A 98768bd8ba13
know-what-a-change-costs is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,065 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 2026-08-31.
Other skills, from other repositories
claude-project-manifest
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
proofpress
Preserve or inspect decision history for Markdown and static HTML knowledge artifacts with Proofpress. Use when creating or accepting a meaningful revision to an ADR, design doc, PRD, README, strategy note, portable .md artifact, or static .html/.htm artifact in a configured repository, or when receiving a file…
book-to-skill
Use when convert technical books and documents (PDF, EPUB, DOCX, HTML, Markdown, RTF, MOBI) into structured agent skills with frameworks, mental models, chapter references, and decision rules. Includes full extraction pipeline. Use when the user wants to turn a book or document collection into a reusable agent skill…
llm-wiki
Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.
PBE Extractor
Extract invariant principles from any text — find the ideas that survive rephrasing.
Principle Synthesizer
Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.