How do I install the Frag Cost skill?

Run npx skillmds@latest add zapgun-ai/frag-cost in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Frag Cost skill do?

clawback fragmentation-cost diagnostic It is listed under Coding & Dev Tools on SkillMD.

Is Frag Cost safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Frag Cost?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Frag Cost free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Frag Cost?

zapgun-ai (@zapgun-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Frag Cost by zapgun-ai — Agent Skill

Name: Frag Cost
Author: zapgun-ai

File contents

clawback fragmentation-cost diagnostic

node .skills/frag-cost/scripts/frag_cost.mjs <instance.ARM.ndjson> [more.ndjson ...]

Pass the per-instance turn-logs (e.g. runs/<dir>/instance.A0.ndjson, instance.A5.ndjson), NOT the tee outputs (A0.ndjson/A5.ndjson) — only the per-instance logs carry systemStableKey alongside sessionKey and Anthropic usage. The tee body is pre-clawback and has no stable key.

Why this exists

.skills/bench's prefix-fragmentation table shows how badly the per-request cch rotation split one logical context into many clawback SESSION KEYs (A0 often 100s → A5 1). That is clawback-layer fragmentation. The trap is assuming distinct SESSION KEYs ⇒ Anthropic cold-starts. On build v2.1.145.20b they do NOT: a fully fragmented A0 (336/336 distinct keys) still read ~~92.7k tokens warm on its fresh-key turns vs ~968 created (95.8×), 98.6% hit. Anthropic serves the prefix warm despite cch rotation, so de-fragmentation buys only the tiny creation delta (~~1.8% on a tight loop), not rescued cold-starts. This skill makes that fresh-vs-repeat cut explicit so the fragmentation count is never mis-sold as token cost.

Reading the output

fresh key (rotated) vs repeat key (stable) mean usage — the decisive cut. read >> creation on fresh keys ⇒ served WARM ⇒ fragmentation is not a cold-start proxy on this build. creation >> read ⇒ fragmentation really is cold-starting ⇒ strip-ephemeral has token value in that regime.
first-in-stream — each stream's opening turn; genuine cold-starts by nature (high creation), reported separately so they don't contaminate the fresh-vs-repeat comparison. Watch for old analyses that sampled these and mislabeled their natural cold-start as cch poisoning.
VERDICT line states the read/create ratio and the conclusion.

Where this sits

Static, post-hoc, zero new tokens. Run it after any .skills/paired or .skills/ab block. Pair it with the zero-token .skills/inspect (static breakpoint structure — the theoretical upper bound) to contrast prediction (inspect) against ground truth (this).

---name: frag-costdescription: clawback fragmentation-cost diagnostic---# clawback fragmentation-cost diagnostic`node .skills/frag-cost/scripts/frag_cost.mjs <instance.ARM.ndjson> [more.ndjson ...]`Pass the **per-instance** turn-logs (e.g. `runs/<dir>/instance.A0.ndjson`,`instance.A5.ndjson`), NOT the tee outputs (`A0.ndjson`/`A5.ndjson`) — only theper-instance logs carry `systemStableKey` alongside `sessionKey` and Anthropic`usage`. The tee body is pre-clawback and has no stable key.## Why this exists`.skills/bench`'s prefix-fragmentation table shows how badly the per-request`cch` rotation split one logical context into many clawback SESSION KEYs (A0often 100s → A5 1). That is clawback-layer fragmentation. The trap is assumingdistinct SESSION KEYs ⇒ Anthropic cold-starts. On build v2.1.145.20b they doNOT: a fully fragmented A0 (336/336 distinct keys) still read ~92.7k tokens**warm** on its fresh-key turns vs ~968 created (95.8×), 98.6% hit. Anthropicserves the prefix warm despite cch rotation, so de-fragmentation buys only thetiny creation delta (~1.8% on a tight loop), not rescued cold-starts. This skillmakes that fresh-vs-repeat cut explicit so the fragmentation count is nevermis-sold as token cost.## Reading the output- **fresh key (rotated)** vs **repeat key (stable)** mean usage — the decisive cut. `read >> creation` on fresh keys ⇒ served WARM ⇒ fragmentation is not a cold-start proxy on this build. `creation >> read` ⇒ fragmentation really is cold-starting ⇒ strip-ephemeral has token value in that regime.- **first-in-stream** — each stream's opening turn; genuine cold-starts by nature (high creation), reported separately so they don't contaminate the fresh-vs-repeat comparison. Watch for old analyses that sampled these and mislabeled their natural cold-start as cch poisoning.- **VERDICT** line states the read/create ratio and the conclusion.## Where this sitsStatic, post-hoc, zero new tokens. Run it after any `.skills/paired` or`.skills/ab` block. Pair it with the zero-token `.skills/inspect` (staticbreakpoint structure — the theoretical upper bound) to contrast prediction(inspect) against ground truth (this).

Frequently asked questions

Frag Cost