agentistics AGENTS.md

AGENTS.md instructions for blpsoares/agentistics, covering before starting implementation work, opening a pr, documentation, scope discipline and discussions.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/blpsoares/agentistics/agents-md
Clone the repo
git clone --depth 1 https://github.com/blpsoares/agentistics

Made for: Codex, OpenCode.

Per session 980 This file is loaded in full into every session.
When invoked 980 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00980 $0.00980
Opus 5 $0.00490 $0.00490
Sonnet 5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured today against content hash 03da48627251, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentistics 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 today.

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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — process rules for any AI coding assistant working in this repo

This file follows the agents.md convention and is read by AI coding harnesses (Claude Code, Codex CLI, Cursor, Amp, Jules, Gemini CLI, and any other tool that supports it). It defines the process every harness must follow when doing implementation work in this repo — Issues, the Project board, Discussions, and documentation. It does not duplicate architecture or implementation detail: those live in docs/ (canonical) and in each harness's own config (CLAUDE.md for Claude Code).

Before starting implementation work

  1. Check the Project board and open Issues for an item that already covers the task. If none exists, open one — use the bug_report or feature_request issue template as fits the change.
  2. New Issues land on the board automatically (.github/workflows/project-add.yml). Set:
    • StatusBacklog on creation, In progress once work actually starts, In review once a PR is open, Done when it merges. Don't leave a card silently stale in the wrong column.
    • PriorityP0 / P1 / P2. Ask the user if it's unclear; never guess P0.
  3. Architecture-affecting or breaking changes get a Discussion first, in the Ideas category, before an Issue is opened — link the Issue back to the Discussion once it exists. Skip this step for bug fixes, docs-only changes, and scoped features that don't change a public contract (an API route, the SessionMeta shape, a CLI flag, the HarnessAdapter contract, a stored document shape, etc.). When in doubt, open the Discussion — reverting a merged breaking change is far more expensive than a skipped conversation.

Opening a PR

  • Link the Issue it addressesCloses #N / Fixes #N / Resolves #N in the PR body, when one exists. This is a convention, not an enforced gate: there is deliberately no CI check and no branch protection requiring it — an Issue must never block someone from shipping a fix. Link it because it keeps the Project board accurate, not because something will reject the PR if you don't.
  • Follow CONTRIBUTING.md for setup, running tests, and commit conventions (Conventional Commits, English).
  • Fill in the PR template for real — a "Summary" with no "Motivation" or "Test plan" is not a filled template.

Read the full file on GitHub · 65 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.

  1. today First seen · 65 lines · 980 tokens per session scan A 03da48627251

Subscribe to this mod's changes

agentistics AGENTS.md is an instructions file published in the GitHub repository blpsoares/agentistics (39 stars, last pushed yesterday), licensed MIT. It adds 980 tokens to every session, about $0.0049 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 2026-09-01.