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/forgeyclap/claude-forge/forge-datanpx skills add ForgeyClap/claude-forge --skill forge-datagit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWhat 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 | $0.00050 | $0.01328 |
| Opus 5 | $0.00025 | $0.00664 |
| Sonnet 5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
forge-data 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 2d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge playbook — Data engineering / ETL / dbt
Do not duplicate ECC skills — defer to: systematic-debugging (pipeline failures), /test-coverage (transform test coverage), learn-codebase / forge-deeplearn (prime an existing warehouse before touching it). This file is orchestration only.
A data pipeline's job is to be trustworthy and repeatable, not just to "run once". The failure mode here is silent: a load that half-succeeds, a duplicate on retry, or a schema change upstream that quietly corrupts a downstream mart while every job still shows green. Treat the warehouse as the product.
Hard rules
- Schema contracts at every boundary. Source and model outputs declare an explicit, enforced schema (dbt model
contracts: enforced, or an explicit column/type check on load). A schema-drift upstream fails the run loudly — never silently coerces or drops columns. - Idempotent + incremental. A rerun produces the same result — no duplicated rows. Incremental loads use a stable unique key (
merge/upsert) and a watermark/high-water-mark;append-only without a dedupe key is banned. Backfills are explicit, bounded, and stated (date range / partition), never an unbounded full-table rewrite by accident. - Data-quality tests are part of "done". Not-null / unique / accepted-values / referential (
relationships) tests on key columns, plus a freshness check and a row-count/volume sanity check. A pipeline with zero tests is not shippable. - Lineage is documented. The DAG / column-level lineage is generated or written down (dbt docs / a lineage diagram). No orphan models, no undocumented hop that only lives in someone's head.
- No PII leakage. PII is classified up front; masked, hashed, or tokenized where it lands; never written to logs, never committed to the repo, and access-scoped in the warehouse. Minimize what you collect and keep.
- Reproducible runs. Warehouse/profile credentials in env (never in
profiles.ymlor committed), dependencies pinned, SQL/seeds versioned in git, transformations deterministic (nonow()-driven nondeterminism baked into stored results without a reason). The same code + same input → the same table.
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.
- 2d ago First seen · 39 lines · 50 tokens per session scan A f1058a652373
forge-data is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 50 tokens to every session and 1,328 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
zh-output-example
Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
company-hiring-intelligence
Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…
文档协作
引导用户通过结构化的文档共同编写工作流程。当用户想撰写文档、提案、技术规范、决策文档或类似结构化内容时使用。该工作流程帮助用户高效传递上下文，通过迭代优化内容，并验证文档对读者有效。当用户提到写文档、创建提案、起草规范或类似文档任务时触发。.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.