exclusions

exclusions is a skill for Claude Code from kimsanguine/hplan. It costs 90 tokens per session (847 once invoked), scanned A, original, MIT.

An append-only list of ideas that should not be built, with the reason, competing product, and evidence that could reopen each decision.

In plain words
What is it for?
It helps record exclusions, compare new ideas with earlier entries using text similarity, and route possible matches to further evaluation or a decision log.
Why use it?
It prevents teams from repeatedly reconsidering the same rejected idea without remembering why it was rejected.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; built for gstack.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python3 hplan/scripts/exclusions_registry.py add "AI marketing copy generator" \.

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

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add kimsanguine/hplan
Claude Code
/plugin install hplan

Made for: Claude Code.

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 exclusions

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimsanguine/hplan/exclusions.svg)](https://agentmods.dev/skills/kimsanguine/hplan/exclusions)
Your own site
<a href="https://agentmods.dev/skills/kimsanguine/hplan/exclusions"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/exclusions.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 847 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 5.1 $0.00090 $0.00847
Opus 5 $0.00045 $0.00424
Sonnet 5 $0.00018 $0.00169
Haiku 4.5 $0.00009 $0.00085

Measured 5d ago against content hash 3760ba0d7bd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

exclusions 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/skills/exclusions/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exclusions Registry — Do Not Build, with Reason

Running for: $ARGUMENTS

Core Goal

  • "지금 만들지 않는다"의 영구 메모리를 구축한다. 매 hplan run마다 휘발되지 않도록 harness/exclusions.jsonl append-only.
  • 각 exclusion에 reopen_trigger를 명시 — 어떤 evidence가 잠금을 푸는지 사전 정의 → 같은 아이디어를 6개월 뒤에 다시 들고 와도 같은 자리로 도달.
  • 새 아이디어가 들어오면 token Jaccard + char-bigram Jaccard 최대값으로 collision detect (한국어 형태소 미분리에도 강함).

Trigger Gate

Use This Skill When

  • evidence-rubric 점수가 낮은데 영역이 이미 점유된 것 같을 때
  • 명시적으로 "이건 안 만들 거다"를 기록하고 싶을 때
  • 새 아이디어가 과거 pivot/hold와 겹치는지 확인하고 싶을 때
  • 팀 onboarding — 새 PM이 들어왔을 때 "이건 왜 안 만들었나" 답변 제공

Route to Other Skills When

  • COLLISION 감지 + reopen_trigger 충족 가능 → evidence-rubric 재실행 (수정된 wedge로)
  • COLLISION 감지 + reopen_trigger 충족 불가 → decision-loghold 또는 pivot 기록
  • CLEAR 결과 → Evidence Gate 정상 진행
  • 경쟁 자체를 깊이 분석해야 할 때 → architect/strategy --focus moat 또는 references/competitive-landscape-superpowers-gstack.md

Boundary Checks

  • ❌ 영구 삭제 없음 (append-only). 잘못 추가하면 새 항목으로 supersede.
  • ❌ Jaccard 0.40 threshold는 보수적 default. 한국어 1-2 단어 차이로 miss 가능 — verify 권장.

Inputs

# Add
python3 hplan/scripts/exclusions_registry.py add "AI marketing copy generator" \
  --why "the existing incumbents 점유" \
  --reopen "엔터프라이즈 컴플라이언스 인터뷰 3건+" \
  --competitor "Incumbent A" --competitor "Incumbent B"

# Check
python3 hplan/scripts/exclusions_registry.py check "generic AI marketing copy tool"

# List
python3 hplan/scripts/exclusions_registry.py list

Steps

  1. Always check first when a new idea arrives — even before evidence-rubric.
  2. If COLLISION + reopen unmet → STOP, route to decision-log (hold).
  3. If COLLISION + reopen met → log the meeting evidence, proceed with caveat.
  4. After every pivot or hold decision, call add so future runs don't repeat the mistake.

Outputs

  • harness/exclusions.jsonl (append-only)
  • check returns {verdict: "COLLISION"|"CLEAR", matches: [...]} JSON

Verification

  • add returns an entry with id, ts, reopen_trigger non-empty.
  • check returns COLLISION when overlap ≥ 0.40, CLEAR otherwise.
  • harness/exclusions.jsonl is valid JSONL (one JSON object per line).

Read the full file on GitHub · 73 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 73 lines · 90 tokens per session scan A 3760ba0d7bd9

Subscribe to this mod's changes

exclusions is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 20d ago), licensed MIT. It adds 90 tokens to every session and 847 once invoked, about $0.0005 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 skills, from other repositories

smart-rebase

Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…

sd0xdev/sd0x-harness · 131 tokens

recap-doc

Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…

sd0xdev/sd0x-harness · 114 tokens

test-review

Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.

sd0xdev/sd0x-harness · 56 tokens

feature-dev

Feature development workflow. Use when: implementing features, writing code, running dev loop. Not for: understanding code (use code-explore), reviewing code (use codex-code-review). Output: implemented feature + tests + review gate.

sd0xdev/sd0x-harness · 50 tokens

jira

Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).

sd0xdev/sd0x-harness · 64 tokens

precommit

Pre-commit checks — lint:fix -> build -> test.

sd0xdev/sd0x-harness · 15 tokens