What is succinctly AGENTS.md?

Repository instructions for Succinctly, a Rust library and command-line tool for querying JSON, YAML, and DSV data with compact indexes. They describe the project layout, worktree rules, feature checks, and required build and verification practices.

Use them when modifying Succinctly code, documentation, tests, benchmarks, or command-line features, especially when working with Rust’s optional features or multiple Git worktrees.

They reduce mistakes when an agent changes this repository, such as editing the wrong worktree, overlooking Rust feature gates, or comparing benchmarks that do not measure equivalent validation.

How rust-works/succinctly configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to rust-works/succinctly. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rust-works/succinctly/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/rust-works/succinctly

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rust-works/succinctly/agents-md/github.svg)](https://agentmods.dev/instructions/rust-works/succinctly/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/rust-works/succinctly/agents-md"><img src="https://agentmods.dev/badge/instructions/rust-works/succinctly/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/rust-works/succinctly/agents-md"><img src="https://agentmods.dev/badge/instructions/rust-works/succinctly/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,232 This file is loaded in full into every session.

When invoked 1,232 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01232	$0.01232
Opus 5.5	$0.00493	$0.00493
Sonnet 5.5	$0.00246	$0.00246
Haiku 4.5	$0.00123	$0.00123

Measured 3d ago against content hash 2d8928df6a2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

succinctly 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.

AGENTS.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for Codex when working in this repository. Read the linked reference only when the task needs its detail.

Project

Succinctly is a Rust library and CLI for succinct data structures and semi-indexed JSON, YAML, and DSV queries. Semi-indexing builds a small structural index and materializes values lazily. It performs less validation than a full DOM parser; benchmark comparisons must account for that difference. Start with docs/index.md, ARCHITECTURE.md, and docs/architecture/semi-indexing.md.

src/bits/: bit vectors, rank/select, popcount
src/trees/: balanced parentheses
src/json/, src/yaml/, src/dsv/: semi-indexed formats
src/jq/: query language and evaluator
src/bin/: CLI

The library supports no_std with alloc. Check feature gates when changing code: cli, simd, regex, serde, bench-runner, and the large-data test features.

Worktree discipline

If working in a Git worktree, identify its root and use explicit paths for every Git, build, search, and edit command. Do not assume the shell's current directory is the intended checkout. After the first edit, run git -C <worktree> status --porcelain and confirm the edited file appears there. Before a commit, confirm git -C <worktree> branch --show-current is the feature branch. Create new worktrees outside the repository under $HOME/wrk/work-trees/succinctly/<branch>/.

Query compatibility

succinctly jq follows jq and succinctly yq follows yq. The mode decides behavior, never the input format. Reproduce reference behavior, including inconsistencies, unless it would emit output the reference cannot read back, corrupt or discard a write, or take down the host process. Record every permitted divergence in jq limitations or yq limitations. Decide behavioral forks in this order: permitted divergence, fidelity to the pinned reference, then performance and memory. Put mode-specific rules on EvalSemantics, not per-format traits. See ADR-0018.

Read the full file on GitHub · 60 lines

Changes

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 Changed · +29 tokens per session 2d8928df6a2c
8d ago Changed · +18 tokens per session d16f305b8b18
1mo ago Changed · +4 lines · +134 tokens per session 5126bb25fe18
1mo ago Changed · +1 lines · +22 tokens per session 90d3f6e1b64d
1mo ago Changed · +2 lines · +84 tokens per session 63df0504324e
1mo ago First seen · 53 lines · 945 tokens per session scan A 9d2adf33eaab

Subscribe to this mod's changes

succinctly AGENTS.md is an instructions file published in the GitHub repository rust-works/succinctly (52 stars, last pushed yesterday), licensed MIT. It adds 1,232 tokens to every session, about $0.0049 per session on Opus 5.5. 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 2026-09-23.

Git and workflow Languages Rust

succinctly AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
succinctly AGENTS.mdrust-works/succinctly	Instructions file	52	yesterday	MIT	A	1,232	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

succinctly: Instructions file for Codex