Borrowing it
Nothing to install: this file belongs to sondera-ai/sondera-coding-agent-hooks. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sondera-ai/sondera-coding-agent-hooks/main/AGENTS.mdgit clone --depth 1 https://github.com/sondera-ai/sondera-coding-agent-hooksWrote 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/sondera-ai/sondera-coding-agent-hooks/agents-md)<a href="https://agentmods.dev/instructions/sondera-ai/sondera-coding-agent-hooks/agents-md"><img src="https://agentmods.dev/badge/instructions/sondera-ai/sondera-coding-agent-hooks/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 5.1 | $0.01502 | $0.01502 |
| Opus 5 | $0.00751 | $0.00751 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
sondera-coding-agent-hooks 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 7d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Rust workspace: a reference monitor for AI coding agents. Hook adapters normalize each agent's events, a gRPC harness adjudicates them against Cedar policies, and the decision goes back to the agent.
Commands
The local gate is fmt plus clippy scoped to what you touched. Run these, and only these, before handing work back:
cargo fmt --all # no build; sub-second
cargo clippy -p <crate> --all-targets -- -D warnings # once per crate you changed
cargo check -p <crate> is the faster signal while iterating; clippy subsumes
it at the end.
Run only when the change calls for it:
cargo doc --no-deps -p <crate> # you renamed a public item or edited a [`Type`] link
Leave these to CI unless you are explicitly asked to run them. Each is a full workspace build and is not part of the local loop:
cargo clippy --all-features -- -D warnings # the gate CI enforces
cargo doc --no-deps --workspace # CI enforces doc links
cargo test --workspace # CI runs this
A cold target/ — first build after a branch switch or a cargo update —
makes even a scoped clippy take minutes. That is the build, not the gate: do
not respond to it by skipping the gate or by widening the scope to amortize it.
Provider-gated integration tests are #[ignore]d and need a live model
provider. Do not enable them to "check your work"; CI does not run them either.
Run the stack locally:
cargo run -p sondera -- serve -v # harness + console gRPC on 127.0.0.1:50051
cargo run -p sondera -- tui # read-only view of a running server
cargo run -p sondera -- hook claude install # wire hooks into .claude/settings.local.json
cargo run -p sondera -- mcp # Cedar policy-authoring MCP server on stdio
Where things live
| You're changing | Go to | Read first |
|---|---|---|
| A Cedar policy or the schema | .sondera/policies/cedar/ |
.agents/skills/autoformalize/SKILL.md |
| How an event becomes a Cedar context | crates/policy/cedar/src/transform.rs |
base.cedarschema, which documents every field |
| One agent's hook wiring or response shape | crates/hooks/<provider>/ |
crates/hooks/README.md |
| Behaviour shared by all providers | crates/hooks/core/ |
same |
| Domain types crossing crate boundaries | crates/types/ |
— |
| Shared LLM provider support | crates/provider/ |
crates/provider/src/lib.rs |
What .sondera/ means and how it resolves |
crates/settings/ |
crates/settings/src/lib.rs, which owns the config semantics |
| The gRPC wire format | crates/schema/proto/ |
regenerate via crates/schema/build.rs |
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.
- 7d ago First seen · 117 lines · 1,502 tokens per session scan A c49c2297e556
sondera-coding-agent-hooks AGENTS.md is an instructions file published in the GitHub repository sondera-ai/sondera-coding-agent-hooks (223 stars, last pushed 4d ago), licensed MIT. It adds 1,502 tokens to every session, about $0.0075 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.