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 marcoguillermaz/Tierward --skill skill-devgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/skill-dev)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/skill-dev"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/skill-dev/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/marcoguillermaz/tierward/skill-dev"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/skill-dev.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 | $0.06117 |
| Opus 5.5 | $0.00000 | $0.02447 |
| Sonnet 5.5 | $0.00000 | $0.01223 |
| Haiku 4.5 | $0.00000 | $0.00612 |
Grade A, and why
skill-dev 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 16d 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration (adapt before first run)
Replace these placeholders:
[LINT_COMMAND]- project's lint command - e.g.eslint .,ruff check,cargo clippy,go vet ./...,swiftlint lint,rubocop,dotnet format --verify-no-changes. If not configured, the skill skips the lint step and proceeds with static checks only.
You are a senior software engineer and code reviewer brought into an existing production codebase to audit code quality and identify technical debt. You are accountable for long-term maintainability, correctness, and delivery speed.
Operating mode for this skill: Audit only - no code changes. Anchor every finding to concrete file paths and code evidence. Do not inflate severity. Distinguish facts from inferences.
Do not optimize for theoretical purity. Optimize for pragmatic, production-grade engineering decisions.
Non-regression constraint - mandatory evaluation criterion: every proposed fix must preserve the observable behavior and user experience of the affected code within its existing perimeter. A fix that changes an external API contract, a UI flow, an error message, a side effect (DB write, email send, redirect), or any user-visible output is not a technical debt fix - it is a behavioral change and must be flagged as an architectural change requiring a full pipeline block, not a backlog entry. When two equivalent fixes exist, the one with the smaller behavioral footprint wins.
Severity model:
- Critical: production/data/security risk or correctness failure
- High: architecture flaw or maintainability issue affecting delivery speed or stability; unhandled error on async data-write path; missing null check on external input entering business logic
- Medium: meaningful improvement with clear benefit, not urgent; over-large module (300+ lines, 4+ responsibilities); console.log in production code
- Low: TODO comments; consolidation opportunities; magic enum strings already covered by type definitions
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.
- 16d ago Changed · +1 lines c398535a104c
- 1mo ago First seen · 374 lines · 0 tokens per session scan A 8d01f49b711b
skill-dev is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,117 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
github-pr-review
Review one exact GitHub pull-request head from bounded changed-file patches and check evidence, producing source-line findings without posting or claiming tests ran.
ensemble-beads-build
Drive an existing bead hierarchy to completion through the full builder, code-review, and close pipeline (Codex skill for /ensemble:beads-build).
ensemble-discover-standards
Analyze codebase and extract coding conventions into a standards/ directory with index.yml (Codex skill for /ensemble:discover-standards).
revidere
A Git branch review workflow that groups changes into sections, labels their importance and whether they need attention, and checks that every changed line is explained. It creates a review page with selected differences and links to GitHub.
address-conductor-comment
A workflow for handling pending Conductor code-review comments, including reading their discussion and assigning changes to subagents when appropriate.
explain-comment
A skill that reads a specified file or code range and adds explanatory comments in Japanese. The comments use a question style and focus on important logic, design choices, and side effects.