forge-product-map

forge-product-map is a skill for Claude Code, Codex from SidCorp-co/forge. It costs 140 tokens per session (1,521 once invoked), scanned A, original, Apache-2.0.

A documentation tool that records user journeys, scenarios, workflows, and business rules as Mermaid diagrams. Mermaid is a text format for drawing diagrams.

In plain words
What is it for?
Use it to create an initial product map, refresh documentation after released work, or document one missing scenario. It covers user-facing product behavior, not internal code structure.
Why use it?
It keeps product behavior documented in a curated, visual form and requires each diagram step to be traceable to a real issue, acceptance criterion, or user-facing route.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sidcorp-co/forge/forge-product-map
Any agent
npx skills add SidCorp-co/forge --skill forge-product-map
Clone the repo
git clone --depth 1 https://github.com/SidCorp-co/forge

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for forge-product-map

README.md
[![agentmods](https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-product-map.svg)](https://agentmods.dev/skills/sidcorp-co/forge/forge-product-map)
Your own site
<a href="https://agentmods.dev/skills/sidcorp-co/forge/forge-product-map"><img src="https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-product-map.svg" alt="Measured on agentmods" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,521 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00140 $0.01521
Opus 5 $0.00070 $0.00760
Sonnet 5 $0.00028 $0.00304
Haiku 4.5 $0.00014 $0.00152

Measured 4d ago against content hash 979d9f6bfae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-product-map 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.

packages/core/skills/forge-product-map/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

forge-product-map

Maintains a project's curated product knowledge as Mermaid visual entries. Writes overview, scenario, workflow, and rule entries via forge_knowledge action=upsert. All diagrams represent user-facing product behaviour — never internal implementation.

Modes

  • bootstrap (default) — full sweep: read existing entries, read shipped issues for evidence, identify gaps, ask the human only for gaps that cannot be inferred. Write/refresh all entry kinds.
  • refresh — incremental: read recently closed/released issues since the last run, update existing entries that those issues affect, add missing scenarios.
  • gap [scenarioName] — produce or fill exactly ONE scenario entry. Ask the human for the scenario name if not provided.

Hard verification gate (AC5 — non-negotiable)

Before writing ANY node into a scenario or workflow diagram:

  1. Every node must map to one of: a real issue id, an acceptance criterion phrase, or a user-facing route string (e.g. /projects/:slug/library).
  2. NO file:line, function names, module names, or source-code identifiers as nodes. If a node names a file or function, DELETE it — replace with the user-facing action it implements.
  3. Tag each entry:
    • confidence: "verified" when a shipped (closed/released) issue directly backs the node.
    • confidence: "inferred" when derived from comments, ACs, or reasonable inference.
  4. Store backing issue ids in metadata.relatedIssueIds: string[].

Violating this gate produces diagrams that rot when the code changes. Product diagrams must survive a complete rewrite of the implementation.

Source priority

Read sources in this order; later sources are used only when earlier ones are insufficient:

  1. Existing knowledge entriesforge_knowledge action=list (then action=get for full bodies). These are already curated; update rather than replace.
  2. Shipped issuesforge_issues action=list with status=closed or status=released. Read acceptanceCriteria, description, and comments for evidence of real user flows.
  3. Semantic searchforge_knowledge action=search scope=all query="<topic>" for context not in the entry list.
  4. The human — ask ONLY for gaps that none of the above sources can fill. Batch all gap questions into a single message.

Read the full file on GitHub · 110 lines

Changes

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.

  1. 4d ago First seen · 110 lines · 140 tokens per session scan A 979d9f6bfae9

Subscribe to this mod's changes

forge-product-map is a skill published in the GitHub repository SidCorp-co/forge (5 stars, last pushed today), licensed Apache-2.0. It adds 140 tokens to every session and 1,521 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

ai-seo

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…

rondoflow/rondoflow · 191 tokens

ad-creative

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…

rondoflow/rondoflow · 142 tokens

ads

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…

rondoflow/rondoflow · 135 tokens

ai-agent-job-marketplace

The job marketplace where bots hire bots. Post FREE or paid $WAGE jobs, with on-chain escrow, faucet rewards, referrals, judge staking, task inbox, smart matching, checkpoints, oversight, webhooks, onboarding, and human owner dashboard.

rondoflow/rondoflow · 56 tokens

adaptive-anti-bot-web-scraping

Adaptive web scraping framework with anti-bot bypass and spider crawling.

rondoflow/rondoflow · 23 tokens

agent-freelance-bounty-marketplace

Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup. Guilds, ranks, vouching, disputes, Castle Town, leaderboard.

rondoflow/rondoflow · 68 tokens