analyze-arcs SKILL.md skillA
analyze-arcs from turbokach/claude-code-setup is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add turbokach/claude-code-setup/analyze-arcs@git:20261023.4f454b1Pins git:20261023.4f454b1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- turbokach/claude-code-setup
- Path
skills/analyze-arcs/SKILL.md- Versions recorded
- 16
- Latest version
- git:20261023.4f454b1, committed Oct 23, 2026
- First version recorded
- Sep 13, 2026
- Size
- 10,933 bytes
- Repository stars
- 11
- License
- MIT
Measure the Claude Code pipeline sessions since a date — master transcripts, their subagents/*.jsonl, and the codex-challenge logs — and report the numbers plus the mechanical doctrine violations. Invoke on "analyze the sessions", "how did the last arcs go", "evaluate the pipeline", "/analyze-arcs <since-date>", or before any kit change that claims to fix a pipeline problem.
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
# Analyze arcs The scripts are read-only. Times in the report are UTC; transcripts are under `~/.claude/projects/<project>/<session>.jsonl` with subagent transcripts beside them in `<session>/subagents/`. The master transcript is a partial record: owner↔subagent messages and everything a subagent did live only in the subagent files, so never judge an agent from the master's view of it. ## Procedure 1. **Version diff first.** `claude --version` against the stamp in the kit's `docs/references.md`; if they differ, read the changelog between them before blaming the doctrine for a harness change. 2. **Run the measurement** into the session scratchpad: ``` python3 ~/.claude/skills/analyze-arcs/scripts/analyze.py --since YYYY-MM-DD --out <scratchpad>/arcs/report.md ``` One section per session id: copies of a transcript under several project directories are reported once, from the largest (then the lexicographically last directory), and the header counts the `<id>.jsonl` copies skipped. A set-aside `<id>.orphaned-…jsonl` copy, a previous transcript of the session, never beats a live `<id>.jsonl` …
Read the whole file at its exact version.
How to install
mdr add turbokach/claude-code-setup/analyze-arcs@sha256:75a55c9d60f834f0The line at the top of this page pins the label git:20261023.4f454b1, 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_kdxlwofkb4jkdoku)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 16 versions of this file, between Sep 13, 2026 and Oct 23, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261023.4f454b1 latest | 2026-10-23 | 4f454b1 | 10,933 B | A | view · diff |
| git:20261023.fbb08ff | 2026-10-23 | fbb08ff | 10,843 B | A | view · diff |
| git:20261023.f923955 | 2026-10-23 | f923955 | 10,745 B | A | view · diff |
| git:20261023.6c31196 | 2026-10-23 | 6c31196 | 9,401 B | A | view · diff |
| git:20261023.ce37acd | 2026-10-23 | ce37acd | 9,037 B | A | view · diff |
| git:20260928.8f1cf37 | 2026-09-28 | 8f1cf37 | 7,453 B | A | view · diff |
| git:20260928.b6e7581 | 2026-09-28 | b6e7581 | 7,374 B | A | view · diff |
| git:20260927.ea5b4d4 | 2026-09-27 | ea5b4d4 | 7,374 B | A | view · diff |
| git:20260924.2b5f31f | 2026-09-24 | 2b5f31f | 7,425 B | A | view · diff |
| git:20260924.21af10c | 2026-09-24 | 21af10c | 7,503 B | A | view · diff |
| git:20260923.6d78855 | 2026-09-23 | 6d78855 | 7,119 B | A | view · diff |
| git:20260920.b04ab81 | 2026-09-20 | b04ab81 | 7,110 B | A | view · diff |
| git:20260918.f2b0b85 | 2026-09-18 | f2b0b85 | 6,827 B | A | view · diff |
| git:20260914.1ee7218 | 2026-09-14 | 1ee7218 | 6,790 B | A | view · diff |
| git:20260913.aad644a | 2026-09-13 | aad644a | 6,769 B | A | view · diff |
| git:20260913.b526a66 | 2026-09-13 | b526a66 | 6,077 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 (10933 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
turbokach/claude-code-setup · 11 stars · license MIT · pushed 2026-10-31 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_kdxlwofkb4jkdoku GET https://markdownregistry.com/api/v1/resolve?ref=turbokach/claude-code-setup/analyze-arcs GET https://markdownregistry.com/api/v1/blob/75a55c9d60f834f08438d3a114e8ce26e1e3e5cb99ea3536620c5131215fab78
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.