What is Cognitive-Assistant AGENTS.md?

A set of instructions for the Cognitive-Assistant codebase, a project organised as one shared pipeline with separate existential and operational profiles. It explains the repository layout and the commands for building or testing each profile.

Listing profiles, ingesting data, building prompts and skills, creating agent files, and running the project’s shared or profile-specific commands.

It helps a coding agent follow the project’s structure, choose the right profile, and run the documented workflow.

How Cody-W-Tucker/Cognitive-Assistant configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Cody-W-Tucker/Cognitive-Assistant. 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/Cody-W-Tucker/Cognitive-Assistant/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Cody-W-Tucker/Cognitive-Assistant

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/cody-w-tucker/cognitive-assistant/agents-md/github.svg)](https://agentmods.dev/instructions/cody-w-tucker/cognitive-assistant/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/cody-w-tucker/cognitive-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/cody-w-tucker/cognitive-assistant/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/cody-w-tucker/cognitive-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/cody-w-tucker/cognitive-assistant/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 714 This file is loaded in full into every session.

When invoked 714 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	$0.00714	$0.00714
Opus 5.5	$0.00286	$0.00286
Sonnet 5.5	$0.00143	$0.00143
Haiku 4.5	$0.00071	$0.00071

Measured 1mo ago against content hash e588b712a657, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Cognitive-Assistant 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 1mo 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines for Cognitive-Assistant

Full documentation for the Cognitive-Assistant project is in docs/.

Layout

The repo is one unified pipeline parameterized by a layer profile.

core/                 unified pipeline (one set of scripts)
profiles/<name>/      profile-specific inputs (questions.csv, prompts/)
workspaces/<name>/    runtime data (data/, artifacts/) per profile
lib/                  shared infrastructure (config, llm, prompts, health)
scripts/              shell launchers and utility entry points
tests/                profile-aware health tests

Two profiles are registered: existential and operational.

CLI

Profile-specific build commands take --profile existential|operational.

# Shared commands
python -m core list-profiles
python -m core enhance-skill
python -m core build-translation-layer
python -m core build-alignment-spec

# Existential profile workflow
python -m core --profile existential ask-questions
python -m core --profile existential build-prompts
python -m core --profile existential build-skills

# Operational profile workflow
python -m core --profile operational ingest-corpus                 # batch
python -m core --profile operational ask-questions
python -m core --profile operational build-prompts
python -m core --profile operational build-skills
python -m core --profile operational build-tool-specs

# Profile-aware validation
python -m core --profile <name> health-check

# Alignment spec generation
python -m core build-alignment-spec

Subcommands that don't apply to a profile (e.g. build-tool-specs --profile existential) fail with a clear error rather than silently no-op.

build-skills writes canonical generated skills to workspaces/skills/<profile>/<skill>/SKILL.md for generated profile skills. Manual imports can still live under purpose categories like workspaces/skills/workflow/<skill>/SKILL.md. build-translation-layer reads from both profiles and writes the orchestrator translation layer (INTERACTION_POSTURE.md and SOUL.md) to workspaces/alignment/artifacts/. build-alignment-spec reads unified skills and writes the alignment spec. update runs the full pipeline: per-profile stages (including build-skills), then cross-profile stages (build-translation-layer + build-alignment-spec).

Read the full file on GitHub · 91 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.

1mo ago Changed · -11 lines · -180 tokens per session e588b712a657
2mo ago First seen · 102 lines · 894 tokens per session scan A cd54e43fedc0

Subscribe to this mod's changes

Cognitive-Assistant AGENTS.md is an instructions file published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 714 tokens to every session, about $0.0029 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 2026-08-30.

Building agents

Cognitive-Assistant AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Cognitive-Assistant AGENTS.mdCody-W-Tucker/Cognitive-Assistant	Instructions file	11	11d ago	Apache-2.0	A	714	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

Cognitive-Assistant: Instructions file for Codex