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 agentmods add skills/alanvaa06/forge-master/spec-designnpx skills add alanvaa06/forge-master --skill spec-designgit clone --depth 1 https://github.com/alanvaa06/forge-masterWrote 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/alanvaa06/forge-master/spec-design)<a href="https://agentmods.dev/skills/alanvaa06/forge-master/spec-design"><img src="https://agentmods.dev/badge/skills/alanvaa06/forge-master/spec-design.svg" alt="Measured on agentmods" 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 | $0.00109 | $0.01311 |
| Opus 5 | $0.00055 | $0.00656 |
| Sonnet 5 | $0.00022 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
spec-design 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-design — PRD to Technical Design (Human Gate 1.5)
Produce docs/forge/specs/spec-NNN.md from an approved docs/forge/prd/NNN-name.md: the HOW that sits between the PRD's WHAT and the plan's WHEN. Decisions get made once here, so phase subagents never re-derive architecture inconsistently.
This step is OPTIONAL by design. The loop's philosophy is optimistic defaults — if the task looks small (few phases, obvious structure, no new interfaces), say so and ASK the user as a lettered list (mark one Recommended with a concrete why), never decide yourself:
This task looks small. Proceed with the spec? a) Skip the spec, go straight to
/forge-master:plan-design— Recommended, small task with obvious structure b) Write the spec anyway — you want the design locked before planning
A spec is warranted when any of: multiple components must agree on interfaces, a data model or API contract is being introduced/changed, the PRD's Constraints imply architectural tradeoffs, or lessons.md shows past runs failing on design drift — when these hold, recommend (b) instead. The user picks by replying with a letter.
Subordination rule: the plan (plan-NNN.md) is the ONLY execution contract. The spec is a design reference the plan cites — if they ever conflict, the plan wins and the spec gets corrected.
Step 1 — Load inputs
- Read the approved PRD
docs/forge/prd/NNN-name.md(ask which N if ambiguous). Do not start without an approved PRD — ACs drive the design. - Read
docs/context/memory.md(existing architecture decisions bind you) anddocs/context/lessons.md(past design-related friction). - For an existing codebase: scan the repo structure and conventions — the spec extends what exists, it does not invent a parallel architecture.
- Read
templates/spec-template.md(from this plugin) as the output skeleton.
Step 2 — Design
Fill the template's sections, anchored to PRD IDs throughout:
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.
- 4d ago First seen · 55 lines · 109 tokens per session scan A 3e0c0565af7a
spec-design is a skill published in the GitHub repository alanvaa06/forge-master (1 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,311 once invoked, about $0.0005 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
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
verify-gates
Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…
session-mode
Use when a project has not yet stored session mode, when a user asks for complete arcgentic workflow execution, or when role identity handoff prompts are needed.
agency-roster
Use when a round references agency-agents catalogs, role-family routing, multi-agent identity prompts, or English/Chinese specialist role catalogs.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.