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 aneja5/forge-skills --skill architecture-and-contractsgit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/architecture-and-contracts)<a href="https://agentmods.dev/skills/aneja5/forge-skills/architecture-and-contracts"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/architecture-and-contracts/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/aneja5/forge-skills/architecture-and-contracts"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/architecture-and-contracts.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 | $0.00055 | $0.01805 |
| Opus 5 | $0.00028 | $0.00903 |
| Sonnet 5 | $0.00011 | $0.00361 |
| Haiku 4.5 | $0.00006 | $0.00180 |
Grade A, and why
architecture-and-contracts 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture and Contracts
Overview
Read .forge/prd.md and produce three artifacts: a system architecture document, precise interface contracts per module boundary, and ADRs for non-obvious decisions. Contracts must be specific enough that two engineers can implement different modules independently and integrate without surprises.
When to Use
.forge/prd.mdexists and is complete- System has 2+ modules that need to interact
- Team will work in parallel — contracts prevent integration failures
- Non-obvious tech decisions need to be recorded with rationale
When NOT to Use
- PRD doesn't exist yet — run
spec-driven-developmentfirst - Trivial change touching only one module — skip straight to
tdd - Architecture already exists and contracts are current — just update the affected contract
Common Rationalizations
| Thought | Reality |
|---|---|
| "We don't need contracts for a small feature" | Contracts protect parallel workers — without them, work diverges |
| "I'll define interfaces as I implement" | Interfaces defined during implementation encode accidents as decisions |
| "ADRs are bureaucratic overhead" | ADRs are the only record of why — without them, decisions get relitigated |
| "The architecture is obvious from the PRD" | Make the obvious explicit — it's where disagreements hide |
| "I can keep the architecture in my head" | You can. Your parallel workers can't. |
Red Flags
- Contracts written at function level instead of module boundary level
- Input/output types described in prose instead of typed schemas
- "Error handling: TBD" in any contract
- Architecture document names files and line numbers (these rot)
- ADR is missing a "Decision" section — only has "Context"
.forge/contracts/has no files after this skill runs
Core Process
Step 1: Read the PRD
Read .forge/prd.md. Identify: module list, interaction points, data flows, NFRs that impose architectural constraints.
Step 2: Explore existing architecture
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 · 142 lines · 55 tokens per session scan A 085813e60aff
architecture-and-contracts is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,805 once invoked, about $0.0003 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
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
tdd
Use when implementing features or bug fixes test-first.