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 commands/bborbe/semantic-search/configuregit clone --depth 1 https://github.com/bborbe/semantic-searchWhat 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 | $0.00024 | $0.02143 |
| Opus 5 | $0.00012 | $0.01071 |
| Sonnet 5 | $0.00005 | $0.00429 |
| Haiku 4.5 | $0.00002 | $0.00214 |
Grade B, and why
configure scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo loginctl enable-linger "$USER" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS --max-time 3 http://127.0.0.1:8321/health 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Walk the user through installing semantic-search-http as a background service so every Claude Code session shares one warm indexer. Covers:
- Pre-flight — detect existing instances, skip or add more
- Tool install via
uv tool install - Service unit creation (launchd on macOS, systemd-user on Linux), with optional instance label for multi-instance setups
- MCP registration in Claude config
Process
Step 0: Pre-flight detection
Probe for an existing service:
curl -fsS --max-time 3 http://127.0.0.1:8321/health 2>/dev/null
If it returns {"status":"ok",...}, list existing service units:
- macOS:
launchctl list | grep semantic-search-http - Linux:
systemctl --user list-units 'semantic-search-http*' --no-legend
Also check current MCP registration:
jq '.mcpServers | to_entries[] | select(.key | test("semantic"))' ~/.claude/mcp-personal.json ~/.claude.json 2>/dev/null
Report findings, then ask (single AskUserQuestion):
A semantic-search-http service is already running on port 8321 (instances: ). What would you like to do?
- Skip — already configured
- Add another instance (different port + label)
- Reconfigure existing instance
- 1 (skip) → STOP with summary
- 2 (add instance) → continue with Step 2; in Step 3 ask for instance label + alternative port
- 3 (reconfigure) → continue with Step 2, reuse the existing label, propose unloading old plist before writing new
If no service is running, continue normally with Step 2.
Step 1: Detect platform
uname -s
Darwin→ macOS, use launchd flow (Step 3a)Linux→ Linux, use systemd-user flow (Step 3b)- Other → STOP, report unsupported platform
Step 2: Verify, install, or upgrade the binary
Check if the binary exists:
command -v semantic-search-http || echo "MISSING"
2a: Missing → install
If missing, ask (single yes/no):
semantic-search-httpnot found. Install now viauv tool install(CPU-only)?
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.
- 2d ago First seen · 232 lines · 24 tokens per session scan B d34adfc2ee3b
configure is a command published in the GitHub repository bborbe/semantic-search (2 stars, last pushed 7d ago), licensed BSD-2-Clause. It adds 24 tokens to every session and 2,143 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.