agent-efficiency-audit SKILL.md skillA
agent-efficiency-audit from sorafujitani/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sorafujitani/skills/agent-efficiency-audit@git:20260902.d9838bbPins git:20260902.d9838bb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sorafujitani/skills
- Path
agent-efficiency-audit/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260902.d9838bb, committed Sep 2, 2026
- First version recorded
- Aug 18, 2026
- Size
- 6,004 bytes
- Repository stars
- 8
- License
- MIT
Audit local agent session logs (Codex, Claude Code, Grok, pi) to find where the token budget actually went, then tell the user what to change. Use when a weekly/usage limit burned unexpectedly fast, when the user asks why token consumption is high, whether they are using agents efficiently, which sessions or skills are expensive, or wants a usage/cost review across harnesses.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# agent-efficiency-audit
Answer one question with evidence: **is this person driving agents efficiently, and if not, what exactly should change?**
Never guess from the conversation. Read the logs.
## Core model
A **turn** is one model inference call, not one user message. LLMs are stateless, so every turn re-sends the entire context: system prompt + full history + every tool output so far.
Consequences that drive every finding here:
- Cost scales with the **square** of turn count, not linearly. $\sum_{i=1}^{n}(C_0 + i\,d) = O(n^2)$.
- A tool call returning 250 tokens still bills the whole 130k context.
- Anything read into context is **re-billed on every later turn**. A 10k-token skill read at turn 50 of 800 costs 7.5M, not 10k.
- Cache discounts the price but the tokens are still counted against rate limits.
So the expensive thing is almost never output. It is context that was loaded early and carried far.
## Workflow
1. Establish the window. For a rate-limit complaint, use the real quota window, not a guess:
```sh
python3 scripts/audit.py burn --source codex --days 14
```
…Read the whole file at its exact version.
How to install
mdr add sorafujitani/skills/agent-efficiency-audit@sha256:ae7b3bb7b8d03e5bThe line at the top of this page pins the label git:20260902.d9838bb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_6igwzrkii42m24dw)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 18, 2026 and Sep 2, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260902.d9838bb latest | 2026-09-02 | d9838bb | 6,004 B | A | view · diff |
| git:20260818.6508e45 | 2026-08-18 | 6508e45 | 5,572 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6004 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
sorafujitani/skills · 8 stars · license MIT · pushed 2026-10-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6igwzrkii42m24dw GET https://markdownregistry.com/api/v1/resolve?ref=sorafujitani/skills/agent-efficiency-audit GET https://markdownregistry.com/api/v1/blob/ae7b3bb7b8d03e5b5e92a55f4eaa283d001643e43d88b01c287b14c33ce326d1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.