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 gitRasheed/metis-skill --skill p12-modulargit clone --depth 1 https://github.com/gitRasheed/metis-skillWrote 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/gitrasheed/metis-skill/p12-modular)<a href="https://agentmods.dev/skills/gitrasheed/metis-skill/p12-modular"><img src="https://agentmods.dev/badge/skills/gitrasheed/metis-skill/p12-modular/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/gitrasheed/metis-skill/p12-modular"><img src="https://agentmods.dev/badge/skills/gitrasheed/metis-skill/p12-modular.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 | $0.00635 |
| Opus 5.5 | $0.00000 | $0.00254 |
| Sonnet 5.5 | $0.00000 | $0.00127 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
P12-modular 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 1mo 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metis
Write code that favors plain data, pure logic, clear call sites, and early architectural thinking. These are strong defaults, not rigid laws: follow the surrounding codebase, framework constraints, and language norms when they clearly matter more.
FIRST, name the phase you are in. THEN read the matching phase file below IN FULL before starting, and hold only it plus the Design principles in mind. Do not read the other phase's file — out-of-phase rules dilute in-phase attention.
- Implementing, fixing, or building anything: read
references/implementing.mdnow. - Reviewing a diff, PR, or another agent's work: read
references/reviewing.mdnow.
Design principles
- Start from the call site, by wishful thinking: pretend the perfect helpers already exist, name them the way you would want to call them, and get the top-level usage reading cleanly. If the calling code reads awkwardly, the abstractions are wrong — and you find out before building anything.
- Prefer plain data plus focused functions, modules, or systems over behavior-heavy objects. Draw boundaries around what systems do, not what entities are.
- Choose the simplest state model that matches reality: discriminated unions for mutually exclusive states, composable data for orthogonal features, and a plain flat record when neither pressure exists — do not over-architect the simple case.
- Isolate mutation and I/O near the edges. Orchestration decides what happens; inner helpers do narrow, understandable work. Push ifs up, fors down.
- Assert at boundaries, both where data enters and where it leaves: parsing, persistence, external APIs, state transitions, and function contracts. Check what must be true and, when useful, what must not be.
- Design for the hardest real requirement first, then simplify downward. When elements of a batch can invalidate each other, classify the whole batch before applying any element.
- Trace invariants before adding defensive checks: if an upstream parser, type, or boundary already guarantees the value, do not duplicate the check. Add one only where data crosses a trust boundary or the invariant can drift.
- Prefer self-explaining code with clear, not bloated, names. Comments explain a non-obvious why in one line — never what the code already says.
What ships with it
2 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.
- 1mo ago First seen · 31 lines · 0 tokens per session scan A f917f2fbebcc
P12-modular is a skill published in the GitHub repository gitRasheed/metis-skill (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 635 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 2026-08-31.
Other skills, from other repositories
api-contract-reviewer
Conditional code-review persona, selected when the diff touches API routes, request/response types, serialization, versioning, or exported type signatures. Reviews code for breaking contract changes. Spawned by the ce:review-beta skill as part of a reviewer ensemble.
tactical-ddd
Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model…
dhh-rails-reviewer
Brutally honest Rails code review from DHH's perspective. Use when reviewing Rails code for anti-patterns, JS framework contamination, or violations of Rails conventions.
review-workflow-management
Read-only audit of the HTTP management endpoints (start, status, terminate, pause, resume, raise-event, purge) an app exposes for Dapr Workflows, with DWF-MGT-NNN findings. Use for "review workflow management" or "check workflow HTTP endpoints". To operate runs on Diagrid Catalyst use the catalyst-ai plugin.
review-pubsub-components
Reviews Dapr pub/sub configuration (components, Subscription files, resiliency, dapr.yaml and Aspire wiring) for inline secrets, unsecured brokers, dead-letter topics without retry policies, scopes and app-id or port collisions. Use for "review my pub/sub components" or "audit Dapr pubsub YAML".
review-pubsub-publishing
Reviews Dapr pub/sub publishing code in .NET and Python for swallowed publish failures, wrong pub/sub names, content types, client lifetime, bulk-publish partial failures and payload size. Use for "review my pub/sub publishing code" or "audit Dapr publish calls".