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.
git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizardWrote 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/commands/yesterday-ai/paperclip-plugin-company-wizard/template-check-use-case)<a href="https://agentmods.dev/commands/yesterday-ai/paperclip-plugin-company-wizard/template-check-use-case"><img src="https://agentmods.dev/badge/commands/yesterday-ai/paperclip-plugin-company-wizard/template-check-use-case/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/commands/yesterday-ai/paperclip-plugin-company-wizard/template-check-use-case"><img src="https://agentmods.dev/badge/commands/yesterday-ai/paperclip-plugin-company-wizard/template-check-use-case.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 | $0.00000 | $0.00867 |
| Opus 5 | $0.00000 | $0.00434 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
template-check-use-case 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 11d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template Gap Analysis for Use Case
Analyze the Clipper template system against a provided use case to identify gaps, missing capabilities, and improvement opportunities.
Input
$ARGUMENTS
If no use case is provided, ask the user to describe their use case.
Instructions
You are auditing Clipper's template system (presets, modules, roles, skills, inline goals) against the use case above. Follow the template philosophy: gracefully optimistic, modular, markdown-first.
Step 1: Understand the use case
Break the use case into concrete requirements:
- What roles/agents are needed?
- What workflows/capabilities must exist?
- What initial tasks or goals should be created?
- What integrations or tools are implied?
- Are there human/board tasks (assignTo: "user")?
- What is the expected output (artifacts, docs, code)?
Step 2: Audit existing templates
Read and evaluate the following against the requirements:
-
Presets —
templates/presets/*/preset.meta.json- Does an existing preset cover this use case? Partially?
- If not, should a new preset be created?
- Check inline
goals[]— do any preset goals match the use case objectives?
-
Modules —
templates/modules/*/module.meta.json- Which existing modules are needed?
- Are there capability gaps (workflows the use case needs that no module provides)?
- Check
tasks[]— do initial tasks cover the use case's bootstrapping needs? - Check
goal— does any module carry an inline goal relevant to this use case? - Check
activatesWithRoles— will needed modules activate with the available roles? - Check
dependencies— are there implicit dependencies not declared?
-
Roles —
templates/roles/*/role.meta.json- Which existing roles are needed?
- Are there missing roles (expertise the use case needs that no role provides)?
- Check
capabilities— do roles cover the skills needed for this use case? - Check
reportsTo— does the hierarchy make sense for this use case?
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.
- 11d ago First seen · 87 lines · 0 tokens per session scan A f1090c554669
template-check-use-case is a command published in the GitHub repository Yesterday-AI/paperclip-plugin-company-wizard (171 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 867 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 2026-08-30.
Other commands, from other repositories
mpm-init
Initialize or update project for Claude Code and MPM.
mpm-organize
Organize project files with intelligent consolidation.
mpm-review
Run a code review of the current diff or a PR via trusty-review, with graceful fallback.
mpm-ticket-view
Orchestrate ticketing agent for project management workflows.
mpm-help
Show available MPM commands, agent types, and usage information.
mpm-session-resume
Load context from paused session.