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/blpsoares/agentistics/agents-mdgit clone --depth 1 https://github.com/blpsoares/agentisticsWhat 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 | $0.00980 | $0.00980 |
| Opus 5 | $0.00490 | $0.00490 |
| Sonnet 5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
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.
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
- Check the Project board and open Issues for an
item that already covers the task. If none exists, open one — use the
bug_reportorfeature_requestissue template as fits the change. - New Issues land on the board automatically
(
.github/workflows/project-add.yml). Set:- Status —
Backlogon creation,In progressonce work actually starts,In reviewonce a PR is open,Donewhen it merges. Don't leave a card silently stale in the wrong column. - Priority —
P0/P1/P2. Ask the user if it's unclear; never guessP0.
- Status —
- 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
SessionMetashape, a CLI flag, theHarnessAdaptercontract, 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 addresses —
Closes #N/Fixes #N/Resolves #Nin 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.mdfor 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.
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.
- today First seen · 65 lines · 980 tokens per session scan A 03da48627251
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.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.