Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/bborbe/semantic-search/claude-mdgit clone --depth 1 https://github.com/bborbe/semantic-searchWrote 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.
[](https://agentmods.dev/instructions/bborbe/semantic-search/claude-md)<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="Measured on agentmods" height="20"></a>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 | $0.01667 | $0.01667 |
| Opus 5 | $0.00834 | $0.00834 |
| Sonnet 5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00167 | $0.00167 |
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 3d 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.
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 logscommitted 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
## Unreleasedis 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 - User confirms ->
dark-factory spec approve <name> - dark-factory auto-generates prompts from spec
- Audit prompts ->
/dark-factory:audit-prompt - User confirms ->
dark-factory prompt approve <name> - Start daemon ->
dark-factory daemon(use Bashrun_in_background: true) - dark-factory executes prompts automatically
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.
- 3d ago First seen · 131 lines · 1,667 tokens per session scan A b297a068824c
semantic-search CLAUDE.md is an instructions file published in the GitHub repository bborbe/semantic-search (2 stars, last pushed 8d ago), licensed BSD-2-Clause. It adds 1,667 tokens to every session, about $0.0083 per session on Opus 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.