What is semantic-search CLAUDE.md?

Repository instructions for semantic search over Markdown files, available through MCP or REST, including its release checklist and dark-factory workflow.

Use them when modifying or releasing the semantic-search project, particularly before approving workflows or deciding whether a change has been published.

They clarify how changes are checked, committed, pushed, tagged, and released, including which automatic-release settings actually apply.

How bborbe/semantic-search configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bborbe/semantic-search. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bborbe/semantic-search/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/bborbe/semantic-search

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bborbe/semantic-search/claude-md/github.svg)](https://agentmods.dev/instructions/bborbe/semantic-search/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bborbe/semantic-search/claude-md"><img src="https://agentmods.dev/badge/instructions/bborbe/semantic-search/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bborbe/semantic-search/claude-md"><img src="https://agentmods.dev/badge/instructions/bborbe/semantic-search/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,690 This file is loaded in full into every session.

When invoked 1,690 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01690	$0.01690
Opus 5.5	$0.00676	$0.00676
Sonnet 5.5	$0.00338	$0.00338
Haiku 4.5	$0.00169	$0.00169

Measured 1mo ago against content hash 26a9f4023725, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

semantic-search CLAUDE.md 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 1mo 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.

CLAUDE.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Semantic search over markdown files — MCP + REST modes.

Release Checklist

Before dark-factory prompt approve: walk scenarios/ against the working tree.

autoRelease is off for this repo — .dark-factory.yaml sets no autoRelease key, and dark-factory config resolves it to false. Verified 2026-08-17; check with dark-factory config | grep autoRelease rather than trusting this line. Consequences, traced through the dark-factory source:

A completed prompt calls CommitOnly (pkg/processor/workflow_helpers.go) — it commits locally and logs committed changes (autoRelease disabled, skipping tag).
The branch is not pushed: the push is gated on AutoRelease (pkg/processor/workflow_executor_direct.go).
No tag is cut and ## Unreleased is not renamed. Releasing is a manual step — see docs/releasing-semantic-search.md.

But a second, separate flag does release: .maintainer.yaml sets release.autoRelease: true, so once a commit with ## Unreleased bullets reaches master, the maintainer-watcher bot tags and releases it automatically. The real checkpoint is therefore push, not approve — approving ships nothing, pushing ships everything. Walk the gate before approving anyway, since approve → push is the path of least resistance.

Skip the scenario gate only if git diff $INSTALLED..HEAD --name-only matches no src/**.py | pyproject.toml | Makefile | tests/**.py paths. See docs/releasing-semantic-search.md for the full flow.

Dark Factory Workflow

Never code directly. All code changes go through the dark-factory pipeline.

Complete Flow

Spec-based (multi-prompt features):

Create spec -> /dark-factory:create-spec
Audit spec -> /dark-factory:audit-spec
Approve the spec -> dark-factory spec approve <name>
dark-factory auto-generates prompts from spec
Audit prompts -> /dark-factory:audit-prompt
Approve the prompt -> dark-factory prompt approve <name>
Start daemon -> dark-factory daemon (use Bash run_in_background: true)
dark-factory executes prompts automatically

Read the full file on GitHub · 131 lines

Changes

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.

1mo ago Changed · +23 tokens per session 26a9f4023725
2mo ago First seen · 131 lines · 1,667 tokens per session scan A b297a068824c

Subscribe to this mod's changes

semantic-search CLAUDE.md is an instructions file published in the GitHub repository bborbe/semantic-search (2 stars, last pushed 1mo ago), licensed BSD-2-Clause. It adds 1,690 tokens to every session, about $0.0068 per session on Opus 5.5. 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.

semantic-search CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
semantic-search CLAUDE.mdbborbe/semantic-search	Instructions file	2	1mo ago	BSD-2-Clause	A	1,690	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

semantic-search: Instructions file for Claude Code