claude-forge: Skill for Claude Code

.claude/skills/forge-verify/SKILL.md

forge-verify is a skill for Claude Code from ForgeyClap/claude-forge. It costs 40 tokens per session (874 once invoked), scanned A, original, MIT.

A verification loop that checks an agent’s claim of completion against recorded events and project tickets.

In plain words
What is it for?
It helps verify each agent or work package after completion and perform a final check across the whole run.
Why use it?
It prevents the coordinator from trusting a status message when the underlying work is incomplete or a ticket is still open.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ForgeyClap/claude-forge's own configuration. It tells Claude Code how to work on claude-forge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-forge configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/forge-bin/forge-verify.cjs <run_id> # report only, exit 0/1.

Reuse

Borrowing it

Nothing to install: this file belongs to ForgeyClap/claude-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ForgeyClap/claude-forge/main/.claude/skills/forge-verify/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ForgeyClap/claude-forge

Made for: Claude Code.

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-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-verify.svg)](https://agentmods.dev/skills/forgeyclap/claude-forge/forge-verify)
Your own site
<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-verify"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 874 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00040 $0.00874
Opus 5 $0.00020 $0.00437
Sonnet 5 $0.00008 $0.00175
Haiku 4.5 $0.00004 $0.00087

Measured 5d ago against content hash 149d83a43e96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

forge-verify 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 5d 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.

.claude/skills/forge-verify/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

forge-verify — the verify-loop

Self-improvement substrate (wp-skill-evals, 2026-07-31): before applying this skill, read learnings.md in this skill's own folder and honor its corrections. After a run that produced a genuine correction (an owner fix, a false assumption caught, a preference stated), append it to learnings.md with a date and real evidence — never invent a lesson that didn't happen.

Closes the honesty gap between "an agent said it's done" and "the recorded events actually show it's done." Never trusts a completion claim on its own.

When to use (MANDATORY)

  • After each agent/work-package completes in a /forge run — before the Lead treats that agent's output as final.
  • At the end of the run, before writing the final report — a last honest check across every agent and every ticket the run touched.
  • Whenever the owner asks "did that agent actually finish?" or "check the tickets are really closed."

How to run

node .claude/forge-bin/forge-verify.cjs <run_id>                      # report only, exit 0/1
node .claude/forge-bin/forge-verify.cjs <run_id> --enforce            # report + send mismatches back
node .claude/forge-bin/forge-verify.cjs <run_id> --json               # full machine-readable result
node .claude/forge-bin/forge-verify.cjs <run_id> --root <projectRoot> # target a different project root

Exit code: 0 when there are no mismatches and no open tickets for the run; 1 otherwise — safe to gate a hook/CI step on it.

What it checks (mirrors the dashboard exactly)

Reconstructs per-agent task state from <run>/events.jsonl the same way the Forge Control Center does (forge-dashboard/app.js BACKBONE + taskStatus()): structural milestone events (run_started, agent_completed, lead_review_completed, …) are never counted as a "task"; every other event attributed to an agent is a task, and a task is "done" only when its status genuinely resolves to done. An agent "claims completed" once it has logged agent_completed or subagent_completed. A mismatch is an agent that claims completed while some of its own tasks are still open, running, or failed.

Read the full file on GitHub · 67 lines

Files

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.

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. 5d ago First seen · 67 lines · 40 tokens per session scan A 149d83a43e96

Subscribe to this mod's changes

forge-verify is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 874 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

onboard

Interviews someone about a software project as a whole — the problem it solves, who it serves, what is in and out of scope, the hard constraints, and the domain vocabulary — and writes it up as a project constitution that every later feature specification inherits. Use this at the start of a project, before any…

handarbeit/fabrik · 173 tokens

fabrik-plan

Use when operating as the Fabrik Plan stage agent. This skill guides the design of an implementation approach, producing a concrete plan with task checklist that the Implement stage will follow.

handarbeit/fabrik · 35 tokens

fabrik-implement

Use when operating as the Fabrik Implement stage agent. This skill guides the implementation of a planned feature, following the task checklist to produce committed, tested, pushed code on a feature branch.

handarbeit/fabrik · 38 tokens

fabrik-setup

Bootstrap a project to use Fabrik (the GitHub-Project-driven SDLC pipeline orchestrator that drives Claude Code workers through Specify/Research/Plan/Implement/Review/Validate stages). Use this skill when the user wants to install, set up, initialize, or get started with Fabrik for the first time — especially when…

handarbeit/fabrik · 142 tokens

shepherd-start

Open a focused investigation session for one bug: pull its full tracker detail, load past lessons and triage history, and produce an investigation plan. Use when starting work on a single ticket, after /shepherd-sync has built the backlog.

mshadmanrahman/pm-pilot · 52 tokens

ticket

Write or draft a minimal tracker ticket: a type/parent line, a terse " :" title, and 2 to 4 bullets of what should change and why in product language, and nothing else (no headings, no acceptance criteria, no Out-of-scope block, no verification gate). Project tokens read from .claude/harness/profile.md. Use when…

waqas1412/claude-harness · 0 tokens