banlist

A command set for maintaining names that must not appear in published project content. It separates a committed public list from a private, machine-only list that is not shared.

In plain words
What is it for?
Use it to view, add, or remove banned names in either layer and enforce the rules through documentation checks and local Git hooks.
Why use it?
It prevents sensitive names from leaking into repository output while keeping private machine identifiers out of the public rule list.

Command

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 commands/intentdriven/abcd/banlist
Clone the repo
git clone --depth 1 https://github.com/intentdriven/abcd
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,727 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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.01727
Opus 5 $0.00025 $0.00864
Sonnet 5 $0.00010 $0.00345
Haiku 4.5 $0.00005 $0.00173

Measured yesterday against content hash 45720fd39485, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

banlist 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.

commands/banlist.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/abcd:banlist — banned names, two layers

Some names must not appear in what a repo publishes: a specific agent harness (so the surface stays host-agnostic), a partner's product, a private project whose very name is confidential — and, most sensitively, the user's own machine identifiers: hostnames, device names, and the addresses or prefixes of their private network.

Enforcement splits by sensitivity, because a deterministic CI gate is the right tool for a public banned name and the wrong place for a private one: the rule would have to contain the very string it forbids.

layer store enforced by visibility
public .abcd/docs-lint.json (the banned_tokens family) abcd docs lint in CI, with a per-line escape entries render in full
private .abcd/.work.local/private-names.txt (gitignored) the committed .githooks/pre-commit and .githooks/pre-merge-commit guards, on this machine only entries render by key only

Render both layers (bare)

"${CLAUDE_PLUGIN_ROOT}/abcd" banlist --json

Summarise the JSON: for private, its present flag and each entry's keynever ask for or repeat a private pattern value, which the binary does not emit; for public, each entry's id, severity, pattern, and whether it is managed (verb-owned, id under names/) or hand-curated.

State the private layer's reach as the binary states it: relay the reach sentence the render carries rather than paraphrasing it. Paraphrase drops the second half, and the way it drops is by omission — "protects only machines that have opted in" alone leaves a reader believing an opted-in machine is fully covered. It is not: a hook sees the commits git asks it about, so a fast-forward git pull, a rebase, a git am, a git revert or a cherry-pick bypasses it, as does --no-verify, and that list is not exhaustive. When private.present is false, say that the layer is inactive on this machine — an absent store checks nothing, and silence must never look like protection.

Read the full file on GitHub · 122 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. yesterday First seen · 122 lines · 50 tokens per session scan A 45720fd39485

Subscribe to this mod's changes

banlist is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,727 once invoked, about $0.0003 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 2026-08-31.

Related

Other commands, from other repositories