CLAUDE.md@scripts/agent_compileA

CLAUDE.md@scripts/agent_compile from sysevol-ai/codenib is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.

Install it, pinned
mdr add sysevol-ai/codenib/scripts/agent_compile/CLAUDE.md@git:20260726.23bbca9

Pins git:20260726.23bbca9 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
CLAUDE.md file
Repository
sysevol-ai/codenib
Path
scripts/agent_compile/CLAUDE.md
Versions recorded
3
Latest version
git:20260726.23bbca9, committed Jul 26, 2026
First version recorded
Jun 2, 2026
Size
1,870 bytes
Repository stars
95
License
Apache-2.0

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

# scripts/agent_compile/ — rules

Tooling for the **agent-compile RFC (#133)**: does selecting a per-scenario
*subset* of skills (Compile → Agent → Route) change cost/accuracy vs a plain
agent? Start from [`README.md`](./README.md) — it maps every script to its RFC
phase. Findings: [`docs/experiments/agent_compile.md`](../../docs/experiments/agent_compile.md);
design: [`docs/agent_compile_design.md`](../../docs/agent_compile_design.md).

## Things to know before editing

- **Phase names skip 0 → 2 on purpose.** Scripts exist only for phases that run
  data; Phase 1 (`classify()`) is code + a doc, not a sweep. `run_sweep.py` +
  the consolidated `aggregate.py` drive both Phase 0 and the Phase 2 subset
  sweep (the old `aggregate_phase2.py` was evicted in the scripts dedup). Don't
  "fix" the numbering.
- **Indexes reach the agent through `RepoManifest`.**
  `IndexCompiler.compile_repo()` (in `codenib/compiler/`) builds `bm25` /
  `vector` / `symbol_graph` and writes `repo_manifest.json` — the source of
  truth for what exists, its freshness, and status. Skill contexts load either
  JIT (`build_skill_contexts`, builds missing indexes) or AoT
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sysevol-ai/codenib/scripts/agent_compile/CLAUDE.md@sha256:0b0d337a99a8a708

The line at the top of this page pins the label git:20260726.23bbca9, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7raova7iojsyzds6.svg)](https://markdownregistry.com/a/art_7raova7iojsyzds6)

3 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in sysevol-ai/codenib/scripts/agent_compile/CLAUDE.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of CLAUDE.md from somewhere else? Ask it: where did my CLAUDE.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 3 versions of this file, between Jun 2, 2026 and Jul 26, 2026, about one every 27 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260726.23bbca9 latest2026-07-26 23bbca9 1,870 BA view · diff
git:20260725.1d299f12026-07-25 1d299f1 1,823 BA view · diff
git:20260602.27533972026-06-02 2753397 1,825 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (1870 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

GitHub

sysevol-ai/codenib · 95 stars · license Apache-2.0 · pushed 2026-11-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7raova7iojsyzds6
GET https://markdownregistry.com/api/v1/resolve?ref=sysevol-ai/codenib/scripts/agent_compile/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/0b0d337a99a8a7085303faad236f10fc76ca7d2daa7ab48b7101ce8582052e3f

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: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.

More from sysevol-ai/codenib

CLAUDE.md@.claude CLAUDE.md file
sysevol-ai/codenib · .claude/CLAUDE.md
git:20261029.5a90ce2 · audit A · 95 stars
AGENTS.md AGENTS.md file
sysevol-ai/codenib · AGENTS.md
git:20261107.7249fcf · audit A · 95 stars
CLAUDE.md@codenib/code_chunking CLAUDE.md file
sysevol-ai/codenib · codenib/code_chunking/CLAUDE.md
git:20260726.23bbca9 · audit A · 95 stars
CLAUDE.md@codenib/dataset CLAUDE.md file
sysevol-ai/codenib · codenib/dataset/CLAUDE.md
git:20261016.ed2fa09 · audit A · 95 stars
CLAUDE.md@codenib/graph CLAUDE.md file
sysevol-ai/codenib · codenib/graph/CLAUDE.md
git:20261104.2c5f286 · audit A · 95 stars
AGENTS.md@landing AGENTS.md file
sysevol-ai/codenib · landing/AGENTS.md
git:20261031.ae6ea88 · audit A · 95 stars
explain SKILL.md skill
sysevol-ai/codenib · plugins/codenib/skills/explain/SKILL.md · Explain how something in this repository works, where it is implemented, or what calls it, with every claim tied to…
git:20261116.1ab51d6 · audit B · 95 stars
impact SKILL.md skill
sysevol-ai/codenib · plugins/codenib/skills/impact/SKILL.md · List the tests that the current, uncommitted change can reach, with the call path to each, before finishing a change in…
git:20261116.1ab51d6 · audit B · 95 stars
setup SKILL.md skill
sysevol-ai/codenib · plugins/codenib/skills/setup/SKILL.md · Install CodeNib and prepare this repository's search index and code graph.
git:20261116.1ab51d6 · audit B · 95 stars
thread SKILL.md skill
sysevol-ai/codenib · plugins/codenib/skills/thread/SKILL.md · Read a GitHub issue or pull request in one step, with its discussion, review comments, failing checks, linked threads…
git:20261116.1ab51d6 · audit B · 95 stars
wiki SKILL.md skill
sysevol-ai/codenib · plugins/codenib/skills/wiki/SKILL.md · Open this repository's CodeNib Wiki in a browser, or set the repository up to publish its Wiki on GitHub Pages.
git:20261111.05f2df6 · audit C · 95 stars
CLAUDE.md@test CLAUDE.md file
sysevol-ai/codenib · test/CLAUDE.md
git:20261108.95d17cf · audit A · 95 stars

Every file in sysevol-ai/codenib

Browse by kind, by grade A, or by owner.