harness-exclude

harness-exclude is a command for coding agents from kimsanguine/hplan. It costs 58 tokens per session (607 once invoked), scanned A, original, MIT.

A command for keeping a permanent list of ideas that should not be built, including the specific condition that would justify reconsidering each one. It can add entries, check a new idea for conflicts, or list existing exclusions.

In plain words
What is it for?
Use it to record a rejected product idea and why it was rejected, test a new idea against earlier decisions, or review the stored Do-Not-Build list.
Why use it?
It prevents teams from repeatedly revisiting ideas they already rejected without new evidence. Separate profiles can keep exclusions for different clients or projects apart.

Command

Part of the hplan plugin — 8 skills, 11 commands, 4 agents shipped together

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/kimsanguine/hplan/harness-exclude
Clone the repo
git clone --depth 1 https://github.com/kimsanguine/hplan

Or install hplan, the plugin that ships this one along with the rest of its 8 skills, 11 commands, 4 agents.

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 harness-exclude

README.md
[![agentmods](https://agentmods.dev/badge/commands/kimsanguine/hplan/harness-exclude.svg)](https://agentmods.dev/commands/kimsanguine/hplan/harness-exclude)
Your own site
<a href="https://agentmods.dev/commands/kimsanguine/hplan/harness-exclude"><img src="https://agentmods.dev/badge/commands/kimsanguine/hplan/harness-exclude.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 607 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 $0.00058 $0.00607
Opus 5 $0.00029 $0.00303
Sonnet 5 $0.00012 $0.00121
Haiku 4.5 $0.00006 $0.00061

Measured 5d ago against content hash 6f45caa15990, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-exclude 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 5d 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.

hplan/commands/harness-exclude.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/harness-exclude

Instructions

You manage the hplan exclusions registry for: $ARGUMENTS

Decide sub-command

  • If user is recording a Do-Not-Build → add
  • If user is checking a new idea → check
  • If listing → list

add

python3 hplan/scripts/exclusions_registry.py add "<idea>" --why "<reason>" --reopen "<trigger>" --competitor "<name>" [--competitor "<name>"]. Require --reopen to be an action-shaped condition (e.g., "enterprise compliance interviews 3+"), not vague.

check

python3 hplan/scripts/exclusions_registry.py check "<idea>". Threshold 0.40 by default. If COLLISION, confirm reopen_trigger met before proceeding with other gates.

list

python3 hplan/scripts/exclusions_registry.py list — dump JSONL.

Profile Isolation (per-client / per-project)

Use --profile <name> to maintain separate exclusion registries for different clients or projects:

# Add an exclusion for a specific client
python3 hplan/scripts/exclusions_registry.py add "AI marketing copy generator" \
  --why "Established incumbents cover this" \
  --reopen "3+ enterprise compliance customers request it" \
  --profile client-acme

# Check only client-acme's registry
python3 hplan/scripts/exclusions_registry.py check "AI marketing copy" --profile client-acme

# List all entries for a profile
python3 hplan/scripts/exclusions_registry.py list --profile client-acme

# Global registry (no --profile = default behavior)
python3 hplan/scripts/exclusions_registry.py check "AI marketing copy"

When --profile is omitted, the global registry at harness/exclusions.jsonl is used. Profile registries are stored at harness/profiles/<profile>/exclusions.jsonl. Add harness/profiles/ to .gitignore to prevent client data from being committed.

Output Format

For add:

  1. idex-YYYY-MM-DD-XXXXX
  2. exclusion text, why, reopen_trigger, competitors

For check:

  1. verdict — COLLISION or CLEAR
  2. matches — array of prior exclusions with overlap score
  3. guidance — next action

Read the full file on GitHub · 63 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. 5d ago First seen · 63 lines · 58 tokens per session scan A 6f45caa15990

Subscribe to this mod's changes

harness-exclude is a command published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 607 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.