A project knowledge record for technology choices, tools, and development rules. It documents decisions such as using Node.js, npm, CommonJS modules, and GitHub Actions.

Use it to record and consult a project's technology stack, decisions, rules, related files, and known gaps.

It gives an agent a shared reference for how the project is built and maintained. This helps avoid suggesting changes that conflict with established choices.

stack — Agent by hannsxpeter

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 agents/hannsxpeter/godpowers/stack

Clone the repo

git clone --depth 1 https://github.com/hannsxpeter/godpowers

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 506 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00506
Opus 5	$0.00000	$0.00253
Sonnet 5	$0.00000	$0.00101
Haiku 4.5	$0.00000	$0.00051

Measured yesterday against content hash ef896498fa02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stack 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 yesterday.

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/stack.md · 67 lines

What it actually says

Scope

[DECISION] This pillar captures technology choices for Godpowers.

Context

Stack

[DECISION] Godpowers uses Node.js with CommonJS runtime modules.
[DECISION] Godpowers uses npm as package manager and package distribution mechanism.
[DECISION] Runtime helpers intentionally avoid production dependencies.
[DECISION] GitHub Actions is the CI and publish automation surface.

Decisions

(none)

Rules

(none)

Workflows

(none)

Watchouts

[HYPOTHESIS] Adding a YAML dependency would simplify parsing but would increase package footprint and installation risk.

Touchpoints

[DECISION] Stack decisions synchronize from .godpowers/stack/DECISION.mdx through the managed section below.

Gaps

(none)

Godpowers artifact sources

Sync mode: auto-applied by yolo.
Related artifact: .godpowers/stack/DECISION.mdx.
Rule: keep this pillar aligned when these artifacts change durable stack truth.

Extracted durable signals

From .godpowers/stack/DECISION.mdx:

[DECISION] Candidates evaluated: Node.js CommonJS, Node.js ESM, and a compiled binary.
[DECISION] Scores: CommonJS 9.2, ESM 7.8, compiled binary 6.2.
[DECISION] CommonJS wins because the installer executes directly on Node 18-plus across 15 host layouts without a build step.
[DECISION] Lock-in cost is low because modules use built-in APIs and can migrate file by file.
[DECISION] Candidates evaluated: local files, SQLite, and a hosted service.
[DECISION] Scores: local files 9.1, SQLite 7.4, hosted service 4.9.
[DECISION] Local files win because disk state remains inspectable, offline, versionable, and portable between AI coding tools.
[DECISION] Lock-in cost is low because every canonical format has a documented schema or deterministic parser.

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.

yesterday First seen · 67 lines · 0 tokens per session scan A ef896498fa02

Subscribe to this mod's changes

stack is an agent published in the GitHub repository hannsxpeter/godpowers (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 506 tokens. 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.

agent-orchestration ai-coding claude-code codex cursor developer-tools

ap-framework-generator

L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…

Spielewoy/autoprompt-skill · 93 tokens

stack

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Scope

Context

Stack

Decisions

Rules

Workflows

Watchouts

Touchpoints

Gaps

Godpowers artifact sources

Extracted durable signals

What this file has done since we first saw it

Other agents, from other repositories

ap-framework-generator

ap-juror

ap-verifier

ap-re-anchor

domain

ijfw-extract-learnings