What is DecisionsSearch AGENTS.md?

Project instructions for DecisionsSearch, covering how agents should create and use recorded project decisions and task memories.

Use them while working in the DecisionsSearch project so memory creation, project context, and post-commit follow-up follow the project’s rules.

They define when to ask about the session’s sources, when to suggest recording lasting knowledge, and how to avoid mixing different kinds of history.

How Renzo-Tognella/DecisionsSearch configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Renzo-Tognella/DecisionsSearch. 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/Renzo-Tognella/DecisionsSearch/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Renzo-Tognella/DecisionsSearch

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/renzo-tognella/decisionssearch/agents-md.svg)](https://agentmods.dev/instructions/renzo-tognella/decisionssearch/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/renzo-tognella/decisionssearch/agents-md"><img src="https://agentmods.dev/badge/instructions/renzo-tognella/decisionssearch/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 595 This file is loaded in full into every session.

When invoked 595 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	$0.00595	$0.00595
Opus 5	$0.00298	$0.00298
Sonnet 5	$0.00119	$0.00119
Haiku 4.5	$0.00060	$0.00060

Measured 7d ago against content hash 4f6486f7d1df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

DecisionsSearch 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.

AGENTS.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DecisionsSearch agent instructions

These instructions are project-scoped and apply to agents working on DecisionsSearch.

Current-session choice for standalone memory creation

Before a standalone create-pr-memory, create-business-rule-memory, create-architectural-decision-memory, create-code-pattern-memory or capture-reasoning reads prior turns, ask exactly: “Para preparar esta memória avulsa, quer que eu considere toda a sessão atual ou apenas as fontes que você indicar?” Record the answer in the preview. This choice governs analysis only; it never replaces preview and persistence confirmation.

Do not ask this question or use the current session in decisionssearch-populate-project or decisionssearch-capture. Those batch flows use only their explicitly authorized historical/PR sources and never create a reasoning episode automatically.

Memory awareness after commits and pull requests

After the user says that a commit was created, a pull request was opened, updated, merged, or asks to finalize a change, check whether the work contains durable knowledge that should be proposed to DecisionsSearch.

Do not block or delay the requested Git/PR action. If the user only states an intention to commit or open a PR, wait until a real commit SHA or PR URL/ number exists.
When the DecisionsSearch MCP is available, collect the real commit and PR metadata, session context, changed files, and diff. Prefer memory.capture_commit with dry_run: true; dry-run must not persist or create links.
If the result is no_memory, say that no durable candidate was found and do not force a memory. Trivial formatting, generated files, and one-off changes normally belong here.
If candidates exist, show a short preview with category, title, evidence, and proposed links, then ask exactly one concise question: “Encontrei estas memórias duráveis. Quer que eu persista e relacione?”
Only after an explicit affirmative answer may the agent run the relevant create-* skills and link-pr-to-memory, followed by memory.get and link verification. Keep PRMemory, BusinessRule, ArchitecturalDecision, CodePattern, and reasoning separate.
Do not invent a card, objective, alternative, stakeholder, reasoning, or canonical repository. Historical PRs without session context do not produce a reasoning episode.
A versioned post-commit hook may already have run in the background. Check its idempotency state or existing proposal before repeating work; never turn a second pass into a duplicate memory.

Read the full file on GitHub · 52 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.

7d ago First seen · 52 lines · 595 tokens per session scan A 4f6486f7d1df

Subscribe to this mod's changes

DecisionsSearch AGENTS.md is an instructions file published in the GitHub repository Renzo-Tognella/DecisionsSearch (0 stars, last pushed 14d ago), licensed MIT. It adds 595 tokens to every session, about $0.0030 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.

Memory and context

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

DecisionsSearch: Instructions file for Codex