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/aphelion-development/search-box/agents-mdgit clone --depth 1 https://github.com/Aphelion-Development/search-boxWrote 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/aphelion-development/search-box/agents-md)<a href="https://agentmods.dev/instructions/aphelion-development/search-box/agents-md"><img src="https://agentmods.dev/badge/instructions/aphelion-development/search-box/agents-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 | $0.01135 | $0.01135 |
| Opus 5 | $0.00567 | $0.00567 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
search-box AGENTS.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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — search-box
Use Tero + cabal-devmelopner for work here.
Tero (Layer-1 corpus index)
Repo has docs/tero-index/index.json (generated/ refreshed via tero-mcp/scripts/generate_lite_index.py).
Rule: Use tero queries before large greps or assumptions.
- Grok: tero__text_search / query_by_id (token "local-dev")
- Direct: tero-mcp-lite --index docs/tero-index/index.json
- cabal-devmelopner: auto-detects local index when run from within this tree (or set TERO_INDEX_PATH).
Example:
cd /root/git/search-box
# agent with context:
uv run --project ../cabal-devmelopner cabal-devmelopner "task description here" --use-tero
Citations point at file:line — open them.
Working with cabal-devmelopner agent tool
This project is prepared for integration:
- Tero index committed on chore/tero-index-cabal-ready (and PRable to dev)
- Local auto index support in cabal
- This AGENTS.md
PR flow (protect main/dev):
- Create/checkout feature or chore branch
- Make changes (agent will often use working branch)
- PR the branch →
dev(then dev → main when ready)
Local checks
Look for:
- scripts/check.sh
- Cargo.toml / pyproject.toml + standard commands (cargo test, uv run pytest, ruff, etc.)
Run checks before considering work complete.
Further reading
- README.md
- docs/ROADMAP.md or ROADMAP.md (if present)
- docs/ASSESSMENT.md or similar for intent/gaps
- ../cabal-devmelopner/docs/* for agent architecture
- ../tero-mcp for how indexes are built and served
Leave mycelium isolated; all coordination here targets the other repos + cabal.
Hygiene + tero land status (2026-07-09)
- Task: Land chore/tero + hygiene for search-box (per plan.md priority 1).
- Tero-first: used
/root/git/scripts/tero.sh search-box ...(identify, text_search, etc) before edits/assumptions. - Read plan.md + models (ROADMAP, ASSESSMENT, LOCAL_CHECKS, update-tero.sh, check.sh, etc).
- Checkout dev; merge --no-ff chore/tero-index-cabal-ready; push.
- ./scripts/check.sh : 31 tests passed, green.
- update-tero.sh search-box; committed tero refresh (MANIFEST + prior).
- Merged to main --no-ff; propagated (dev <-> main --no-ff, pushed).
- Appended this status (append-only).
- Verified: branches synced (origin/dev, origin/main current), checks green, tero queries resolve (see docs/tero-index).
- Citations from tero used to open AGENTS:24, ROADMAP:1 etc.
- Note: now tero index + check/AGENTS/LOCAL_CHECKS on main/dev (was only on chore).
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 · 89 lines · 1,135 tokens per session scan A bda36cc9c826
search-box AGENTS.md is an instructions file published in the GitHub repository Aphelion-Development/search-box (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,135 tokens to every session, about $0.0057 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.