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.
npx skills add kimsanguine/hplan --skill evidence-rubricgit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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.
[](https://agentmods.dev/skills/kimsanguine/hplan/evidence-rubric)<a href="https://agentmods.dev/skills/kimsanguine/hplan/evidence-rubric"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/evidence-rubric/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.
<a href="https://agentmods.dev/skills/kimsanguine/hplan/evidence-rubric"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/evidence-rubric.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00112 | $0.01217 |
| Opus 5 | $0.00056 | $0.00609 |
| Sonnet 5 | $0.00022 | $0.00243 |
| Haiku 4.5 | $0.00011 | $0.00122 |
Grade A, and why
evidence-rubric 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Rubric — 100-Point Idea Scoring
Running for: $ARGUMENTS
Core Goal
- 아이디어를 100점 루브릭으로 측정하여 "PRD 쓰기 전에 인터뷰가 더 필요한지" 명확한 신호를 만든다.
- 8개 축 각각의 점수 + 부족한 axis 목록을 반환해서, 다음 인터뷰에서 어떤 신호를 들어야 하는지 좁힌다.
- LLM의 직감 평가가 아닌 결정론적 스크립트(
generate_report.py)로 점수화해 hand-wave를 차단한다.
Trigger Gate
Use This Skill When
- 사용자가 아이디어 한 문장 + 타깃 + 가설 + 대체재 + 기능 후보를 제시했을 때
- Spec-Kit / Kiro / GStack / Superpowers 워크플로우 진입 전
- 이미 인터뷰 노트가 있어 evidence strength를 객관적으로 측정하고 싶을 때
- "build로 가야 할까 interview를 더 해야 할까" 고민이 등장했을 때
Route to Other Skills When
- 점수가 낮고 인터뷰 자체가 부족할 때 →
interview-synthesis(hplan plugin) - 이미 점유된 영역으로 보일 때 →
exclusions(hplan plugin) check - 점수는 충분한데 비용 구조가 불확실할 때 →
cogs-sentinel(hplan plugin) - 아이디어 발굴 단계로 돌아가야 할 때 →
opp-tree(discover plugin)
Boundary Checks
- ❌ 이 skill은 아이디어 발굴이 아니다 (그건
discover/opp-tree). 이미 아이디어가 있을 때만 호출. - ❌ 이 skill은 PRD 작성을 허락하지 않는다. 점수가 충분해도 Product Gate + Build Gate를 거쳐야 한다.
- ❌ 점수만 높고 인터뷰가 0건이면
interview결정이 강제된다.
Inputs
JSON 파일 또는 인라인 입력:
{
"idea": "한 문장 가설",
"target": "ICP 행동 기술 (인구통계 금지)",
"hypothesis": "현재 상황",
"alternatives": "대체재 콤마 구분",
"features": "MVP 기능 후보 콤마 구분",
"interview_notes": "인터뷰 발화 한 줄당 하나"
}
Steps
- Read
examples/good-01.mdto internalize the rubric. - If user input is freeform, structure it into the 6 fields above.
- Save to
harness/evidence/last_input.json. - Run
python3 hplan/scripts/generate_report.py <path> --json. - Report score + decision + breakdown + missing axes.
- If
decision == "interview", immediately route tointerview-synthesisskill. - If
decision == "build", write the report toharness/evidence/report.mdand route tocogs-sentinel.
Outputs
harness/evidence/report.md— markdown diagnosisharness/evidence/last_input.json— preserved input- Decision:
build(≥75 + interview_lines ≥ 2 + economic pain) /interview(≥55, or ≥75 without required conditions) /pivot(35–54) /hold(<35) —buildrequires mandatoryeconomic_pain+ 2+ interview lines; score alone is not sufficient
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.
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.
- 12d ago First seen · 94 lines · 112 tokens per session scan A 9c6249f6c799
evidence-rubric is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 26d ago), licensed MIT. It adds 112 tokens to every session and 1,217 once invoked, about $0.0006 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.
Other skills, from other repositories
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
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…
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.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
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.