taskchad-os: Command for Claude Code

.claude/commands/core_piv_loop/prime-signal.md

prime-signal is a command for Claude Code from TheSmokeDev/taskchad-os. It costs 25 tokens per session (829 once invoked), scanned A, original, MIT.

A command that loads the parts of a project’s assistant system responsible for memory, thinking before replies, beliefs about the operator, detecting contradictions, and evidence-based self-changes.

In plain words
What is it for?
Use it when investigating or modifying cognition, recall, operator modeling, contradiction handling, or self-evolution features.
Why use it?
It gathers the related files in a defined order so the agent can understand how the system recalls information and changes its identity.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is TheSmokeDev/taskchad-os's own configuration. It tells Claude Code how to work on taskchad-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything taskchad-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TheSmokeDev/taskchad-os. 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/TheSmokeDev/taskchad-os/master/.claude/commands/core_piv_loop/prime-signal.md
Clone the repo
git clone --depth 1 https://github.com/TheSmokeDev/taskchad-os

Made for: Claude Code.

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.

agentmods badge for prime-signal

README.md
[![agentmods](https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/prime-signal/github.svg)](https://agentmods.dev/commands/thesmokedev/taskchad-os/prime-signal)
Your own site
<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/prime-signal"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/prime-signal/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.

agentmods 80×15 button for prime-signal

Your own site · 80×15
<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/prime-signal"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/prime-signal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 829 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00829
Opus 5 $0.00013 $0.00415
Sonnet 5 $0.00005 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 10d ago against content hash 7b185788f767, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prime-signal 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 10d 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.

.claude/commands/core_piv_loop/prime-signal.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prime: Signal / Cognition Slice

Objective

Build understanding of The Homie's cognitive system — how it recalls, thinks before speaking, forms beliefs about the operator, detects contradictions, and evolves its own identity files through evidence-gated amendments. This is the "Make The Self Real" program: Living Mind (sense/remember/brief) + Living Self (form/hold/earn beliefs).

Key Files to Read

Read these files in order. The cognition modules live in .claude/chat/cognition/; the evolution engine lives in .claude/scripts/evolve/.

Architecture doc (read first — Living Self section)

@.claude/sections/03_memory_pipelines.md

Core recall pipeline

@.claude/chat/recall_service.py @.claude/chat/cognition/recall.py

Region assembly (how context reaches the prompt)

@.claude/chat/cognition/regions.py @.claude/chat/cognition/identity_payload.py

Cognitive pass (think before speaking)

@.claude/chat/cognition/cognitive_pass.py @.claude/chat/cognition/processes.py @.claude/chat/cognition/proactive_actions.py

Operator modeling (Act 1 — model the operator from verbatim turns)

@.claude/chat/cognition/operator_beliefs.py @.claude/chat/cognition/self_model.py @.claude/chat/cognition/capture.py

Contradiction engine (Act 2)

@.claude/chat/cognition/belief_conflicts.py

Evidence gate + amendments (Act 4)

@.claude/chat/cognition/evidence_gate.py @.claude/chat/cognition/amendments.py

Self-evolution loop (Archon-driven)

@.claude/scripts/evolve/evolve_loop.py @.claude/scripts/evolve/judge.py @.claude/scripts/evolve/belief_regression.py

Session opening brief (Living Mind Act 4)

@.claude/chat/cognition/proactive_brief.py

Architecture Manual

@docs/the-living-self-manual.md

Slice Boundaries

  • Owns: recall pipeline (tier classification, dual search, graph traversal), region assembly, cognitive pass, operator belief extraction, contradiction detection, evidence-gated amendments, belief evolution loop, session opening brief
  • Does NOT own: memory persistence pipelines (.claude/scripts/memory_*.py — see /prime-memory), chat routing (.claude/chat/router.py), runtime provider selection
  • Cross-slice touchpoints: engine.py calls cognition modules for region assembly, recall, and cognitive pass; memory pipelines call recall for search; evolve loop reads/writes SOUL.md and SELF.md

Read the full file on GitHub · 86 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. 10d ago First seen · 86 lines · 25 tokens per session scan A 7b185788f767

Subscribe to this mod's changes

prime-signal is a command published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 829 once invoked, about $0.0001 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 2026-08-30.