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/stahldavid/sensegrep/agents-mdgit clone --depth 1 https://github.com/Stahldavid/sensegrepWrote 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/stahldavid/sensegrep/agents-md)<a href="https://agentmods.dev/instructions/stahldavid/sensegrep/agents-md"><img src="https://agentmods.dev/badge/instructions/stahldavid/sensegrep/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 | $0.01172 | $0.01172 |
| Opus 5 | $0.00586 | $0.00586 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
sensegrep 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cursor Cloud specific instructions
What this repo is
sensegrep is an npm workspaces monorepo (TypeScript, Node >=20). There are no Docker services or long-running HTTP servers. Development centers on building packages and running Node CLIs:
| Package | Role | After npm run build |
|---|---|---|
packages/core |
Search engine (@sensegrep/core) |
packages/core/dist/ |
packages/cli |
CLI (sensegrep) |
node packages/cli/dist/main.js |
packages/mcp |
stdio MCP server | node packages/mcp/dist/server.js |
packages/vscode |
VS Code/Cursor extension | npm run dev --workspace sensegrep (esbuild watch) |
The demo/ folder is a separate Remotion project (not in workspaces); only needed for marketing video scripts.
Standard commands (see also CONTRIBUTING.md)
- Install:
npm ci(CI uses lockfile;npm installalso works) - Build:
npm run build(node build.js— core → cli → mcp) - Typecheck:
npm run check(runsprecheck→ build, then workspacetsc) - Tests:
npm test(Vitest; no API keys required) - Version consistency:
npm run version:check
Root npm run dev is a placeholder; use package-specific commands above.
Lint / format
There is no ESLint/Prettier at the repo root. “Lint” for this repo means npm run check (TypeScript --noEmit per workspace).
Semantic index and search (remote embeddings)
Indexing and semantic search use remote embeddings only. CI does not configure providers.
Recommended: Cohere via Amazon Bedrock (Bedrock API key)
Default model: cohere.embed-v4:0 (1536-dim). Global inference ID: global.cohere.embed-v4:0 via embedModel in config.
Authentication is either:
- Bedrock API key (prefix
ABSK…) inapiKey— bearer token, notAWS_ACCESS_KEY_ID/AWS_SECRET_ACCESS_KEY, or - IAM via the AWS SDK default chain (no
apiKeyin config).
Canonical config file — ~/.config/sensegrep/config.json:
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 · 92 lines · 1,172 tokens per session scan A 7a80c7c439bd
sensegrep AGENTS.md is an instructions file published in the GitHub repository Stahldavid/sensegrep (1 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1,172 tokens to every session, about $0.0059 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
chunkhound AGENTS.md
AGENTS.md instructions for chunkhound/chunkhound, covering chunkhound llm context, projectidentity, modificationrules, keycommands and development.
chunkhound CLAUDE.md
Claude Code instructions for chunkhound/chunkhound, a project described as: Your entire engineering context, deeply understood.
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
octocode AGENTS.md
AGENTS.md instructions for Muvon/octocode, covering octocode — ai-powered code intelligence, project structure, where to look, how things work and configuration — no defaults rule.
codesearch AGENTS.md
Instructions for flupkede/codesearch, covering agents.md — codesearch, current state, implemented features, open todos and ⚠️ branching & pr workflow (read first).
codesage AGENTS.md
Instructions for iliaal/codesage, covering codesage, build, sanity check before pushing, crate map and search pipeline.